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

    Neuronpedia

    INDEX
    Explanations

    products and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    特定の
    0.52
    鹖
    0.52
    文字列
    0.51
     prést
    0.50
    㫴
    0.48
    書法
    0.47
    侾
    0.46
    絟
    0.46
    とのこと
    0.46
    のだろう
    0.46
    POSITIVE LOGITS
     who
    0.54
     by
    0.50
    de
    0.50
     er
    0.49
     is
    0.48
     identifies
    0.47
     Kü
    0.47
    by
    0.46
     CrossFit
    0.45
     Williams
    0.45
    Act Density 0.021%

    No Known Activations