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

    Neuronpedia

    INDEX
    Explanations

    ’s

    np_max-act · gemini-2.0-flash

    The neuron responds to common sentence-linking or discourse words (e.g., “The,” “And,” “That,” “This,” “is,” “and”) which introduce or connect ideas.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (!
    -0.07
     Hide
    -0.07
    PORT
    -0.07
     vurgu
    -0.06
    ='
    -0.06
    )'),↵
    -0.06
    .gb
    -0.06
     Canter
    -0.06
     (('
    -0.06
     +/-
    -0.06
    POSITIVE LOGITS
    Began
    0.06
    &t
    0.06
     questionnaire
    0.06
    خذ
    0.06
     노하우
    0.06
    vest
    0.06
    éfono
    0.06
    structures
    0.06
    én
    0.06
    _UID
    0.06
    Act Density 0.048%

    No Known Activations