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

    Neuronpedia

    INDEX
    Explanations

    introducing conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     هناك
    -1.76
     navegar
    -1.60
     queremos
    -1.57
     transportar
    -1.54
     呢
    -1.54
    噔
    -1.52
    umento
    -1.50
     capturar
    -1.50
    Ꮠ
    -1.48
     habilitar
    -1.48
    POSITIVE LOGITS
    因素
    1.52
    ㆆ
    1.50
    霙
    1.48
     kupa
    1.46
    ...).
    1.46
    0
    1.46
     HIEROGLYPH
    1.45
    今も
    1.45
    ัณฑ
    1.44
    無く
    1.43
    Act Density 0.016%

    No Known Activations