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

    Neuronpedia

    INDEX
    Explanations

    Searches key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    0.61
    4
    0.51
    5
    0.50
    ↵↵
    0.50
    a
    0.48
    r
    0.48
    y
    0.48
    6
    0.48
     You
    0.47
    0
    0.47
    POSITIVE LOGITS
    ensureEqual
    0.55
    犇
    0.53
     फिल्में
    0.52
    投标
    0.52
    apadani
    0.50
     تیار
    0.49
     kı
    0.49
     امریکی
    0.49
    Shore
    0.49
    ᡧ
    0.49
    Act Density 0.000%

    No Known Activations