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

    Neuronpedia

    INDEX
    Explanations

    audience / user / reader

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    movies
    0.96
     kelamin
    0.91
    populations
    0.89
    machines
    0.88
    arı
    0.85
     berkaitan
    0.82
    peasants
    0.82
    kup
    0.82
    northern
    0.81
    <0x8C>
    0.81
    POSITIVE LOGITS
    슨
    0.85
     in
    0.84
     from
    0.76
    ся
    0.74
    จาก
    0.74
     lasso
    0.73
    ہ
    0.72
    ؤں
    0.70
    ICIENCY
    0.69
     dexterity
    0.69
    Act Density 0.114%

    No Known Activations