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

    Neuronpedia

    INDEX
    Explanations

    reson

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    False
    -0.06
     Cuisine
    -0.06
    inch
    -0.06
     desserts
    -0.06
     legit
    -0.06
     although
    -0.06
    Bulk
    -0.06
    ород
    -0.06
    黃
    -0.06
     psychologists
    -0.06
    POSITIVE LOGITS
    ogene
    0.07
     jan
    0.07
     �
    0.07
    <lemma
    0.07
     přih
    0.06
     searcher
    0.06
    ›
    0.06
     �
    0.06
    _experiment
    0.06
     svým
    0.06
    Act Density 0.002%

    No Known Activations