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

    Neuronpedia

    INDEX
    Explanations

    withdrawal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -mean
    -0.07
     говор
    -0.06
     Dispatcher
    -0.06
     occurrence
    -0.06
    -sort
    -0.06
    _scaled
    -0.06
     happened
    -0.06
    จะเป
    -0.06
     Samar
    -0.06
     міс
    -0.06
    POSITIVE LOGITS
     withdraw
    0.11
     withdrawal
    0.10
     withdrew
    0.09
     withdrawals
    0.09
     deduct
    0.08
     withdrawn
    0.08
    withdraw
    0.08
    атков
    0.08
     Withdraw
    0.07
    Withdraw
    0.07
    Act Density 0.006%

    No Known Activations