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

    Neuronpedia

    INDEX
    Explanations

    scientific experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dev
    -0.07
    \:
    -0.06
    walls
    -0.06
    (nc
    -0.06
    .position
    -0.06
     cig
    -0.06
    <Audio
    -0.06
     TouchableOpacity
    -0.06
     Prov
    -0.06
    limits
    -0.06
    POSITIVE LOGITS
     INTERN
    0.07
     KK
    0.07
     (::
    0.06
     ('
    0.06
    очной
    0.06
     Graves
    0.06
     achieved
    0.06
    urette
    0.06
     Dummy
    0.06
     Invalid
    0.06
    Act Density 0.026%

    No Known Activations