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

    Neuronpedia

    INDEX
    Explanations

    horizontal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    es
    0.91
    ej
    0.83
    anfaatkan
    0.77
    ad
    0.75
    as
    0.75
     Ры
    0.75
     চৈ
    0.75
    ara
    0.70
    and
    0.70
    tand
    0.70
    POSITIVE LOGITS
    Less
    0.81
     sterilized
    0.81
     presently
    0.79
     sanitized
    0.79
     disputed
    0.79
     aseptic
    0.78
    ulières
    0.77
     也
    0.76
     placés
    0.76
     hardwoods
    0.76
    Act Density 0.001%

    No Known Activations