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

    Neuronpedia

    INDEX
    Explanations

    Smithsonian Magazine, Wolfram Alpha

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     relation
    0.61
    0.59
    get
    0.58
    relation
    0.58
    -
    0.56
     a
    0.56
    act
    0.56
    res
    0.56
    rate
    0.56
     r
    0.55
    POSITIVE LOGITS
    🆓
    0.69
     선정
    0.68
    𒐪
    0.67
    btnEjercicio
    0.65
     ಇಸ್ಕೊ
    0.65
     Labrenzia
    0.64
    🔈
    0.64
     videomuz
    0.64
    tAux
    0.63
     strListName
    0.63
    Act Density 0.079%

    No Known Activations