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

    Neuronpedia

    INDEX
    Explanations

    citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     highways
    -0.07
    _median
    -0.07
     provision
    -0.07
     penetration
    -0.07
    (factor
    -0.07
    marca
    -0.07
     ست
    -0.07
    otti
    -0.07
    ','
    -0.06
    _gettime
    -0.06
    POSITIVE LOGITS
    [DllImport
    0.06
    DIFF
    0.06
    alex
    0.06
    leftright
    0.05
    この
    0.05
    _minimum
    0.05
     Alter
    0.05
     합니다
    0.05
     favourites
    0.05
     kız
    0.05
    Act Density 0.007%

    No Known Activations