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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chal
    -0.07
     دام
    -0.06
    beer
    -0.06
    phetamine
    -0.06
     nhé
    -0.06
    jím
    -0.06
    viders
    -0.06
     trừ
    -0.06
    níku
    -0.06
    :UIControl
    -0.06
    POSITIVE LOGITS
    _merged
    0.08
    CONFIG
    0.08
    Upgrade
    0.07
     ｲ
    0.07
     una
    0.07
    _UNKNOWN
    0.07
    уч
    0.06
    report
    0.06
    ační
    0.06
    isce
    0.06
    Act Density 0.000%

    No Known Activations