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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Shot
    -0.07
     sci
    -0.06
    ி�
    -0.06
     sample
    -0.06
     UserControl
    -0.06
    applications
    -0.06
     reversible
    -0.06
    ferences
    -0.06
     legit
    -0.06
     Xt
    -0.06
    POSITIVE LOGITS
    (cv
    0.07
     immer
    0.07
    _BIND
    0.07
     "..
    0.06
    만원
    0.06
    باب
    0.06
    ndata
    0.06
    /Branch
    0.06
    _second
    0.06
     rites
    0.06
    Act Density 0.044%

    No Known Activations