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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    providedIn
    -2.70
    the
    -2.03
    —
    -1.90
    borderSide
    -1.79
    Thus
    -1.79
    at
    -1.79
    0
    -1.77
     diseñada
    -1.76
     menyen
    -1.75
    you
    -1.73
    POSITIVE LOGITS
     hábit
    2.14
    慳
    2.11
    饪
    2.02
     concentrado
    2.00
     parlak
    1.96
    ナイキ
    1.95
     secciones
    1.90
     observado
    1.88
    喏
    1.88
    為に
    1.82
    Act Density 0.031%

    No Known Activations