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

    Neuronpedia

    INDEX
    Explanations

    introducing new names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /__
    -0.88
    mặt
    -0.84
    厥
    -0.78
    ariats
    -0.77
     брюки
    -0.74
    (/*
    -0.74
    andingan
    -0.73
    фото
    -0.73
     Mrs
    -0.71
    ácia
    -0.71
    POSITIVE LOGITS
    vertis
    0.88
    urz
    0.85
    лович
    0.84
     redistribute
    0.82
    ALB
    0.81
    Otras
    0.81
    Descargar
    0.79
    domés
    0.79
     bagay
    0.76
    Ɂ
    0.76
    Act Density 0.005%

    No Known Activations