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

    Neuronpedia

    INDEX
    Explanations

    question answering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erness
    -0.07
    请
    -0.06
    offline
    -0.06
    048
    -0.06
     Highlight
    -0.06
     年
    -0.06
    erp
    -0.06
    057
    -0.06
    HOOK
    -0.06
     систем
    -0.06
    POSITIVE LOGITS
     움직
    0.06
     самое
    0.06
     Jehovah
    0.06
    UPI
    0.06
     Cliff
    0.06
    cly
    0.06
     misleading
    0.06
    alsex
    0.06
     productions
    0.06
     CHR
    0.06
    Act Density 0.223%

    No Known Activations