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

    Neuronpedia

    INDEX
    Explanations

    retired professions and withdrawal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.60
     Reunion
    0.48
     Reun
    0.46
     redis
    0.45
    גים
    0.44
    工作室
    0.43
    ini
    0.43
    ’
    0.42
     Ay
    0.42
    obil
    0.42
    POSITIVE LOGITS
     withdrawal
    1.10
     withdraw
    1.06
     withdrawing
    1.05
     retirada
    1.02
    withdrawal
    1.02
     Withdraw
    1.01
     Withdrawal
    0.98
    Withdraw
    0.98
    withdraw
    0.96
     withdrawn
    0.93
    Act Density 0.026%

    No Known Activations