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

    Neuronpedia

    INDEX
    Explanations

    death or harm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sprites
    -0.07
    wat
    -0.07
     counter
    -0.07
     Dalton
    -0.06
    _wave
    -0.06
     bursts
    -0.06
     Universidad
    -0.06
    ner
    -0.06
     Logs
    -0.06
     Tuple
    -0.06
    POSITIVE LOGITS
    Выб
    0.07
    ività
    0.07
    ."""↵↵
    0.06
     encour
    0.06
     журн
    0.06
     tüm
    0.06
    měr
    0.06
    Ò
    0.06
    _clip
    0.06
    otal
    0.06
    Act Density 0.030%

    No Known Activations