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

    Neuronpedia

    INDEX
    Explanations

    Countries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     __('
    -0.07
     crises
    -0.07
    omers
    -0.07
    ो।
    -0.06
     وذلك
    -0.06
     Door
    -0.06
     orderly
    -0.06
    408
    -0.06
     tuner
    -0.06
    ITION
    -0.06
    POSITIVE LOGITS
    ////////////////////////////////////////////////////////////////////////////////↵
    0.06
     nécess
    0.06
    千
    0.06
     bdsm
    0.06
    icycle
    0.06
     Cook
    0.06
     Qualität
    0.06
     places
    0.06
     ninete
    0.06
     emploi
    0.06
    Act Density 0.009%

    No Known Activations