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

    Neuronpedia

    INDEX
    Explanations

    correctly predicted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     terrifying
    0.50
     frightening
    0.47
     limpieza
    0.45
     sinister
    0.44
    谋
    0.44
    ل
    0.43
    发动
    0.42
    etera
    0.41
    FindAction
    0.41
    epers
    0.41
    POSITIVE LOGITS
    notifications
    0.52
     ಹೆಸರು
    0.51
    ']+
    0.49
    colorChoice
    0.49
     ಹೊಂದಿದೆ
    0.49
     Affidavit
    0.49
    configs
    0.48
    help
    0.47
    deaths
    0.47
    updates
    0.47
    Act Density 0.004%

    No Known Activations