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

    Neuronpedia

    INDEX
    Explanations

    to obtain or avoid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     revolves
    0.84
     exists
    0.71
    どのように
    0.69
    izable
    0.68
     extrêmement
    0.67
     posits
    0.67
     variously
    0.66
     undertakes
    0.66
    ulates
    0.65
    非常に
    0.65
    POSITIVE LOGITS
     avoid
    2.08
     obter
    1.89
     evitar
    1.83
     избежать
    1.73
    获得
    1.73
    避免
    1.73
     obtener
    1.72
     mendapatkan
    1.72
     get
    1.70
     menghindari
    1.68
    Act Density 0.079%

    No Known Activations