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

    Neuronpedia

    INDEX
    Explanations

    subtle signs, data, liability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.66
    0.56
    S
    0.51
     s
    0.50
    :
    0.50
     h
    0.49
    ih
    0.49
    ari
    0.48
     to
    0.47
    at
    0.46
    POSITIVE LOGITS
    𝓸
    0.57
    okkh
    0.52
     یو
    0.51
     matemático
    0.49
    一脸
    0.49
    dostęp
    0.49
    𝗈
    0.49
    LogRow
    0.48
    )]^{
    0.48
     procéd
    0.48
    Act Density 0.000%

    No Known Activations