Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    vandalism

    np_max-act · gemini-2.0-flash

    phrases and words related to vandalism or acts of destruction.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on occurrences of the root “vandal,” i.e. words referring to vandalism (e.g. “vandalism,” “vandalized,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ...↵↵↵↵
    -0.07
    middleware
    -0.06
    _STOP
    -0.06
     trouver
    -0.06
    
    -0.06
    ěř
    -0.06
     nový
    -0.06
    OUSE
    -0.06
     mời
    -0.05
    irect
    -0.05
    POSITIVE LOGITS
     vandal
    0.11
     vandalism
    0.10
     graffiti
    0.08
     mutil
    0.08
     DIY
    0.07
     kid
    0.07
     القدم
    0.07
    Ze
    0.07
     GIF
    0.07
    188
    0.07
    Act Density 0.002%

    No Known Activations