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

    Neuronpedia

    INDEX
    Explanations

    Mixed data sources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    下的
    -0.07
     Substitute
    -0.07
    Password
    -0.06
     pově
    -0.06
     öner
    -0.06
    ';';
    -0.06
    istrat
    -0.06
     virtually
    -0.06
    ай
    -0.06
     addObject
    -0.06
    POSITIVE LOGITS
     مفهوم
    0.06
     pragmatic
    0.06
    (UnityEngine
    0.06
     methodologies
    0.06
    揮
    0.06
    otation
    0.06
    isten
    0.06
    vern
    0.06
    utors
    0.06
    _losses
    0.06
    Act Density 0.000%

    No Known Activations