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

    Neuronpedia

    INDEX
    Explanations

    familiarity with something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </i>
    -1.80
    ↵
    -1.75
    繝
    -1.68
     だっ
    -1.64
     to
    -1.64
     diğer
    -1.63
    してた
    -1.58
     econó
    -1.56
    蹰
    -1.52
    堕
    -1.49
    POSITIVE LOGITS
    ⩥
    1.91
    的一個
    1.82
     какое
    1.77
    ();
    1.77
     Füßen
    1.74
    槩
    1.74
    纐
    1.68
    尔夫
    1.62
    玙
    1.61
    fang
    1.59
    Act Density 0.010%

    No Known Activations