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

    Neuronpedia

    INDEX
    Explanations

    cleared

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     выше
    -0.06
     Jing
    -0.06
     prostituerte
    -0.06
    see
    -0.06
    setTimeout
    -0.06
     mill
    -0.06
    아파트
    -0.06
     Suicide
    -0.06
     acre
    -0.06
     brid
    -0.06
    POSITIVE LOGITS
    ้งาน
    0.07
    ENCED
    0.07
     souha
    0.06
    TRL
    0.06
    Multiple
    0.06
     Стар
    0.06
     şans
    0.06
     kesinlikle
    0.06
     تلك
    0.06
    _song
    0.06
    Act Density 0.000%

    No Known Activations