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

    Neuronpedia

    INDEX
    Explanations

    Emmy Awards, set pieces, law acts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۔
    0.61
    对象
    0.59
    edor
    0.58
     статті
    0.57
    encoding
    0.55
    )。
    0.54
    jst
    0.54
    dell
    0.54
    :“
    0.53
     Printable
    0.53
    POSITIVE LOGITS
     реаги
    0.62
     powied
    0.61
    u
    0.60
    ță
    0.57
     développ
    0.57
     environ
    0.54
    ש
    0.53
     myster
    0.52
     avantages
    0.49
     বলেছি
    0.49
    Act Density 0.000%

    No Known Activations