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

    Neuronpedia

    INDEX
    Explanations

    Stand with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AT
    0.49
     鳥
    0.47
     pessoais
    0.46
     piccoli
    0.45
     Aufnahme
    0.44
     quando
    0.43
     когда
    0.43
    महा
    0.43
     U
    0.43
    大丈夫
    0.43
    POSITIVE LOGITS
    졌
    0.46
    贡献
    0.43
    inear
    0.42
    ished
    0.41
    p
    0.41
    én
    0.41
    ensing
    0.41
    爱情
    0.40
    ู่
    0.40
    hement
    0.40
    Act Density 0.006%

    No Known Activations