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

    Neuronpedia

    INDEX
    Explanations

    celebrating and investing in futures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nemmeno
    0.52
     argu
    0.49
     vált
    0.49
     subito
    0.49
     davvero
    0.49
     نہيں
    0.48
     Tài
    0.48
     ವಿರು
    0.48
    ৩২
    0.47
     próp
    0.47
    POSITIVE LOGITS
    0.66
    re
    0.53
    -
    0.53
    t
    0.49
    s
    0.49
    ab
    0.48
    un
    0.46
    :
    0.45
    _
    0.42
    together
    0.42
    Act Density 0.000%

    No Known Activations