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

    Neuronpedia

    INDEX
    Explanations

    Java

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     сет
    -0.07
    >Description
    -0.07
    .response
    -0.07
    の場合
    -0.07
     либо
    -0.07
     பட்ட
    -0.07
     ringtone
    -0.07
    stored
    -0.07
     reprodução
    -0.07
     "#{
    -0.07
    POSITIVE LOGITS
    几年
    0.11
     Verbesser
    0.10
     mejoras
    0.09
     melhorias
    0.09
     Improvements
    0.09
    provements
    0.09
     improvements
    0.09
     anual
    0.08
     בשנת
    0.08
     obligatorio
    0.08
    Act Density 0.009%

    No Known Activations