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

    Neuronpedia

    INDEX
    Explanations

    pops

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gyhoeddwyd
    -0.68
     culture
    -0.63
    InvalidProtocol
    -0.61
     nahilalakip
    -0.59
     estekak
    -0.59
     <=",
    -0.58
    ABAJO
    -0.57
    tagHelperRunner
    -0.57
    Chham
    -0.57
    MessageState
    -0.56
    POSITIVE LOGITS
    IntoConstraints
    0.66
    0.54
     civil
    0.51
    wapV
    0.46
     Crim
    0.46
    getInputStream
    0.45
    CIV
    0.45
    giveness
    0.44
    LLocation
    0.43
    toHaveBeenCalled
    0.43
    Act Density 0.001%

    No Known Activations