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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "};↵
    -0.07
    upported
    -0.07
    AAP
    -0.06
    _set
    -0.06
    δο
    -0.06
    annah
    -0.06
    xAD
    -0.06
    เง
    -0.06
    usters
    -0.06
    军
    -0.06
    POSITIVE LOGITS
     çek
    0.07
     Perhaps
    0.07
    (ERROR
    0.07
    DET
    0.07
    Helmet
    0.06
     Trading
    0.06
    _ADDRESS
    0.06
    (chart
    0.06
     bevor
    0.06
     blew
    0.06
    Act Density 0.001%

    No Known Activations