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

    Neuronpedia

    INDEX
    Explanations

    code and technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ridiculous
    -0.06
     увагу
    -0.06
    _middle
    -0.06
    聖
    -0.06
    _tra
    -0.06
    .')↵
    -0.06
    もり
    -0.06
    기술
    -0.06
    126
    -0.05
    olut
    -0.05
    POSITIVE LOGITS
     dear
    0.09
    važ
    0.08
     RT
    0.07
    .createUser
    0.07
     투
    0.07
    exit
    0.07
     ontvangst
    0.06
     فض
    0.06
    fred
    0.06
    widget
    0.06
    Act Density 0.000%

    No Known Activations