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

    Neuronpedia

    INDEX
    Explanations

    the first, FTP, event, format, ads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    b
    0.62
    g
    0.59
    d
    0.56
    m
    0.56
    !
    0.54
    ’
    0.52
    𝒟
    0.52
    T
    0.51
    tn
    0.50
    h
    0.50
    POSITIVE LOGITS
    一定的
    0.58
    abilità
    0.57
     أيضاً
    0.57
    किसी
    0.57
    ین
    0.56
     കൂടുതല്‍
    0.56
    şik
    0.55
     કોઈ
    0.55
     एखाद्या
    0.54
    یک
    0.54
    Act Density 1.758%

    No Known Activations