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

    Neuronpedia

    INDEX
    Explanations

    sending well wishes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atisf
    0.83
    概念
    0.83
    atisme
    0.82
    関数
    0.82
    静态
    0.80
    捗
    0.79
    函数
    0.78
    deterministic
    0.77
     വിശദ
    0.77
     deterministic
    0.77
    POSITIVE LOGITS
    Sending
    1.63
     Wishing
    1.61
     Sending
    1.59
    Wishing
    1.57
     sending
    1.55
     wishing
    1.48
     sincerely
    1.46
    sending
    1.40
     heartfelt
    1.36
     please
    1.27
    Act Density 0.948%

    No Known Activations