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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Direction
    -0.07
     Syn
    -0.07
     Clark
    -0.07
     audits
    -0.06
    地下
    -0.06
     Triangle
    -0.06
    _subscription
    -0.06
     Superior
    -0.06
    interval
    -0.06
     capacity
    -0.06
    POSITIVE LOGITS
    wię
    0.07
    _$_
    0.06
    :relative
    0.06
     sen
    0.06
     Queensland
    0.06
     boa
    0.06
     �
    0.06
     ensl
    0.06
    ickém
    0.06
     +**************
    0.06
    Act Density 0.103%

    No Known Activations