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

    Neuronpedia

    INDEX
    Explanations

    _n

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skuteč
    -0.07
    Disappear
    -0.07
     svc
    -0.07
     TLC
    -0.06
     chấp
    -0.06
    كييف
    -0.06
     Pixels
    -0.06
    Changing
    -0.06
    ,String
    -0.06
     Fauc
    -0.06
    POSITIVE LOGITS
     Muhammad
    0.08
     swing
    0.06
    シー
    0.06
     prone
    0.06
     🙂
    0.06
     tariffs
    0.06
     m
    0.06
     Intellectual
    0.06
     Urban
    0.06
     Dating
    0.06
    Act Density 0.006%

    No Known Activations