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

    Neuronpedia

    INDEX
    Explanations

    ICATION

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inging
    -0.08
    Coupon
    -0.08
    -video
    -0.07
    終於
    -0.07
    ância
    -0.07
     Grinding
    -0.07
    angel
    -0.07
    indrical
    -0.07
    band
    -0.07
     −
    -0.06
    POSITIVE LOGITS
     stools
    0.08
    Constructed
    0.07
     Feature
    0.07
     Ub
    0.07
     starters
    0.07
     blog
    0.06
     Ara
    0.06
    -used
    0.06
     polo
    0.06
     fuels
    0.06
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.