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

    Neuronpedia

    INDEX
    Explanations

    withdrawal and irritability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wares
    0.40
    inh
    0.39
    illis
    0.39
    wares
    0.38
    udu
    0.38
     সেইরূপ
    0.37
     حدی
    0.37
    wau
    0.36
    MetaData
    0.36
     subjet
    0.35
    POSITIVE LOGITS
     irritability
    1.16
     withdrawal
    0.99
     withdrawing
    0.98
     Withdrawal
    0.96
     withdraw
    0.93
     irritable
    0.93
    withdrawal
    0.93
    irrit
    0.88
     withdrawn
    0.86
    withdraw
    0.85
    Act Density 0.030%

    No Known Activations