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

    Neuronpedia

    INDEX
    Explanations

    trick-or-treating patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     عاي
    0.57
    閆
    0.56
     добав
    0.55
     поверну
    0.54
    出力
    0.53
    ๋ว
    0.53
     دارم
    0.52
    ดวก
    0.52
    🎟
    0.52
    劶
    0.52
    POSITIVE LOGITS
     Chromatography
    0.57
    ler
    0.54
     of
    0.54
     Method
    0.53
     OF
    0.53
    rz
    0.50
     Effect
    0.50
     Evaluation
    0.50
    subject
    0.49
     HANDLING
    0.49
    Act Density 0.000%

    No Known Activations