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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     เส
    -0.07
    /dir
    -0.07
    _circle
    -0.07
    588
    -0.06
    _accepted
    -0.06
    的一个
    -0.06
     Kabul
    -0.06
    _PRIORITY
    -0.06
     Hồng
    -0.06
    柜
    -0.06
    POSITIVE LOGITS
    TO
    0.07
    Toronto
    0.07
     ability
    0.06
    clean
    0.06
     //$
    0.06
     get
    0.06
     파
    0.06
    keeping
    0.06
     (![
    0.06
    ]$
    0.06
    Act Density 0.000%

    No Known Activations