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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CodeGen
    -0.07
    ahoma
    -0.07
     Commerce
    -0.07
    <Date
    -0.06
     Goods
    -0.06
     بوابة
    -0.06
    nehmer
    -0.06
     Schwe
    -0.06
    orting
    -0.06
    '],
    -0.06
    POSITIVE LOGITS
     İst
    0.08
     cub
    0.07
    ゝ
    0.07
     anc
    0.06
     �
    0.06
    _OBS
    0.06
    _AST
    0.06
    _Ref
    0.06
    donnees
    0.06
    ritch
    0.06
    Act Density 0.009%

    No Known Activations