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

    Neuronpedia

    INDEX
    Explanations

    sanctions against

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ים
    0.71
    ના
    0.69
    cience
    0.68
     שם
    0.68
    A
    0.68
     septic
    0.66
    köy
    0.65
     postseason
    0.64
     frontal
    0.63
    transferase
    0.63
    POSITIVE LOGITS
     sanctions
    1.02
     санк
    0.89
    н
    0.79
     are
    0.70
    as
    0.68
     punishments
    0.68
    。
    0.67
     sanciones
    0.66
     organes
    0.66
     exercícios
    0.63
    Act Density 0.002%

    No Known Activations