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

    Neuronpedia

    INDEX
    Explanations

    open source, version control, fine-tuning, legal action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    B
    0.59
    separator
    0.57
    w
    0.56
    u
    0.54
    avak
    0.53
    N
    0.53
    (
    0.52
    ников
    0.52
    the
    0.51
    in
    0.51
    POSITIVE LOGITS
     andre
    0.71
     altres
    0.66
     เพราะ
    0.65
     undertaken
    0.65
     然後
    0.63
    ណៈ
    0.63
    আনুশকা
    0.62
     ขณะ
    0.62
     tandis
    0.61
     sedangkan
    0.61
    Act Density 0.005%

    No Known Activations