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

    Neuronpedia

    INDEX
    Explanations

    measure success

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wnios
    0.56
    ্যালেঞ্জ
    0.55
     simplicial
    0.54
     cytos
    0.54
     middlewares
    0.54
     raincoat
    0.53
     catechol
    0.53
    UIColor
    0.53
     Aquinas
    0.53
    0.53
    POSITIVE LOGITS
    guest
    0.51
    pear
    0.49
    bury
    0.49
    podcast
    0.47
    heiro
    0.47
    giving
    0.47
    pounds
    0.46
     پیسو
    0.46
    esch
    0.45
    sex
    0.45
    Act Density 0.009%

    No Known Activations