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

    Neuronpedia

    INDEX
    Explanations

    First

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    otton
    -0.07
    .encoding
    -0.06
    เซอร
    -0.06
    layout
    -0.06
    ウィ
    -0.06
    _literal
    -0.06
    hões
    -0.06
    -square
    -0.06
    rotation
    -0.06
    :$
    -0.06
    POSITIVE LOGITS
    Ấ
    0.07
    程序
    0.07
     AVR
    0.06
    -range
    0.06
     eyel
    0.06
     Geh
    0.06
    Publication
    0.06
    Attach
    0.06
     timing
    0.06
     repeated
    0.06
    Act Density 0.008%

    No Known Activations