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

    Neuronpedia

    INDEX
    Explanations

    co

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     температу
    -0.07
    ialect
    -0.06
    sheet
    -0.06
    asti
    -0.06
    exchange
    -0.06
    msgs
    -0.06
     bounds
    -0.06
     exceeds
    -0.06
    plusplus
    -0.06
    FAIL
    -0.06
    POSITIVE LOGITS
     parents
    0.07
    _en
    0.06
    児
    0.06
    听到
    0.06
     Joe
    0.06
    _di
    0.06
    
    0.06
     Parents
    0.06
    .Unknown
    0.06
    Family
    0.06
    Act Density 0.015%

    No Known Activations