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

    Neuronpedia

    INDEX
    Explanations

    terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FAMILY
    -0.07
    Species
    -0.07
     Guns
    -0.06
     editions
    -0.06
     Cancer
    -0.06
     carrier
    -0.06
    ्तन
    -0.06
     copied
    -0.06
     xml
    -0.06
     should
    -0.06
    POSITIVE LOGITS
    --[[
    0.07
    /st
    0.07
    =("
    0.06
    .performance
    0.06
    uilt
    0.06
    (Tree
    0.06
    _ec
    0.06
    来的
    0.06
     Fibonacci
    0.06
    substring
    0.06
    Act Density 0.001%

    No Known Activations