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

    Neuronpedia

    INDEX
    Explanations

    code input validation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    注
    -0.09
    -0.08
     注
    -0.08
    ，日本
    -0.07
     Verl
    -0.07
    .schedule
    -0.07
     النو
    -0.07
    Danger
    -0.07
     Spitz
    -0.07
     Luft
    -0.07
    POSITIVE LOGITS
     удовлетвор
    0.10
     satisfactory
    0.10
     satisfying
    0.10
    atisfactory
    0.08
     сф
    0.08
    _accept
    0.08
     aceptación
    0.08
    жал
    0.08
    _valid
    0.08
     improvements
    0.08
    Act Density 0.006%

    No Known Activations