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

    Neuronpedia

    INDEX
    Explanations

    Code and imports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Boot
    -0.07
    erif
    -0.06
     fitting
    -0.06
    /owl
    -0.06
    ================================================================
    -0.06
    活
    -0.06
     humor
    -0.06
    SR
    -0.06
    SED
    -0.06
     supportive
    -0.06
    POSITIVE LOGITS
    .documentElement
    0.07
     entra
    0.07
     prostřed
    0.07
    OTS
    0.06
    .Boolean
    0.06
     شخصی
    0.06
    .currentThread
    0.06
     ="
    0.06
    ToLocal
    0.06
    ท
    0.06
    Act Density 0.040%

    No Known Activations