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

    Neuronpedia

    INDEX
    Explanations

    details/information

    np_max-act · gemini-2.0-flash

    The neuron activates on references to further information or documentation—especially the word “details.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    diğini
    -0.07
    _MB
    -0.07
     AMA
    -0.07
    idente
    -0.07
    хови
    -0.06
    ómo
    -0.06
    RLF
    -0.06
     هذه
    -0.06
    _memory
    -0.06
     alarak
    -0.06
    POSITIVE LOGITS
     �
    0.07
    771
    0.07
    /*@
    0.07
    (Parameter
    0.06
    ":{"
    0.06
    生活
    0.06
     shots
    0.06
    となり
    0.06
     camping
    0.06
     Leaves
    0.06
    Act Density 0.012%

    No Known Activations