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

    Neuronpedia

    INDEX
    Explanations

    Men

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deposit
    -0.07
    PLICIT
    -0.07
     narrator
    -0.07
     Yes
    -0.07
     bou
    -0.07
    _SELECT
    -0.07
     publisher
    -0.07
     Candy
    -0.07
     translate
    -0.06
     calc
    -0.06
    POSITIVE LOGITS
    ETwitter
    0.06
    /epl
    0.06
     quán
    0.06
    '''
    0.06
    Autom
    0.06
    งต
    0.06
    EdgeInsets
    0.05
     أع
    0.05
    Evaluation
    0.05
     duygu
    0.05
    Act Density 0.025%

    No Known Activations