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

    Neuronpedia

    INDEX
    Explanations

    Poland villages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Injected
    -0.07
    -scenes
    -0.07
    ynam
    -0.07
    _sensitive
    -0.07
    posable
    -0.07
    <lemma
    -0.06
     cancers
    -0.06
     Confidence
    -0.06
    -sample
    -0.06
    SimpleName
    -0.06
    POSITIVE LOGITS
     Farr
    0.07
     Solo
    0.07
    所谓的
    0.07
    分类
    0.06
     deux
    0.06
     Both
    0.06
     Di
    0.06
     본
    0.06
    ('''
    0.06
    帮他
    0.06
    Act Density 0.009%

    No Known Activations