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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	msg
    -0.07
    漭
    -0.07
     ecstasy
    -0.07
    .za
    -0.07
    lexical
    -0.07
    ocular
    -0.07
    拜
    -0.07
    nestjs
    -0.07
    	Json
    -0.06
    (tcp
    -0.06
    POSITIVE LOGITS
    (control
    0.07
    真空
    0.06
    곸
    0.06
    _FONT
    0.06
    	job
    0.06
    _one
    0.06
    Ref
    0.06
    $filter
    0.06
     disputed
    0.06
     predictor
    0.06
    Act Density 0.011%

    No Known Activations