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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and code symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     at
    0.46
     popsicle
    0.44
    Literal
    0.44
    。）
    0.43
     kopi
    0.41
    一块
    0.41
     🤗
    0.40
     splurge
    0.39
     والص
    0.39
     私
    0.39
    POSITIVE LOGITS
    ת
    0.86
    us
    0.76
    و
    0.74
    u
    0.69
    ה
    0.59
    ו
    0.59
    ي
    0.57
    ing
    0.57
    ა
    0.57
    т
    0.54
    Act Density 0.035%

    No Known Activations