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

    Neuronpedia

    INDEX
    Explanations

    7

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     moh
    -0.06
     bố
    -0.06
     trotz
    -0.06
    avo
    -0.06
    ='+
    -0.06
    .putText
    -0.06
     sant
    -0.06
    ств
    -0.06
     legend
    -0.06
    _two
    -0.06
    POSITIVE LOGITS
     RADIO
    0.07
     honorary
    0.07
     (::
    0.06
     teaspoons
    0.06
    STS
    0.06
    .ADMIN
    0.06
     پای
    0.06
    随
    0.06
    Kid
    0.06
     eater
    0.06
    Act Density 0.013%

    No Known Activations