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

    Neuronpedia

    INDEX
    Explanations

    Error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .nl
    -0.07
    출장
    -0.06
    ‌پدی
    -0.06
    !!!!!!!!
    -0.06
    etadata
    -0.06
     ο
    -0.06
    tokenizer
    -0.06
    NotSupportedException
    -0.05
    hotmail
    -0.05
     Klo
    -0.05
    POSITIVE LOGITS
    iosk
    0.07
     seeing
    0.07
    '])
    0.07
    .IT
    0.07
     def
    0.07
    ält
    0.07
    ./(
    0.07
    Combat
    0.06
    ']),↵
    0.06
     cartel
    0.06
    Act Density 0.024%

    No Known Activations