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

    Neuronpedia

    INDEX
    Explanations

    programming and command names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SLAs
    0.48
     bút
    0.47
     potongan
    0.46
     inversely
    0.46
    प्टेंबर
    0.46
     innovación
    0.46
     contratación
    0.46
     humanidad
    0.45
     konie
    0.45
     énorme
    0.45
    POSITIVE LOGITS
    -
    0.77
    _
    0.77
    4
    0.64
    2
    0.63
    3
    0.59
    api
    0.56
    5
    0.56
    1
    0.53
    7
    0.53
    ://
    0.52
    Act Density 0.813%

    No Known Activations