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

    Neuronpedia

    INDEX
    Explanations

    X

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anche
    -0.07
     Removed
    -0.06
    anches
    -0.06
    uta
    -0.06
    back
    -0.06
    ,ch
    -0.06
     Sailor
    -0.06
    irling
    -0.06
     Bakery
    -0.06
     removed
    -0.06
    POSITIVE LOGITS
     disciples
    0.07
    арат
    0.06
    Fully
    0.06
    ุษ
    0.06
    .IP
    0.06
    capabilities
    0.06
     fossil
    0.06
    private
    0.06
    annot
    0.06
    Coal
    0.06
    Act Density 0.000%

    No Known Activations