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

    Neuronpedia

    INDEX
    Explanations

    a wide variety of seemingly unrelated words and contexts.

    oai_token-act-pair · gemini-2.0-flash

    academic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.43
    AutoScaleMode
    -0.43
     atras
    -0.40
     usados
    -0.39
     messes
    -0.39
     dấu
    -0.38
    ❋
    -0.38
     resourceCulture
    -0.38
    BASEPATH
    -0.38
     nakalista
    -0.37
    POSITIVE LOGITS
     iſt
    0.69
     Houſe
    0.67
     houſe
    0.66
     Efq
    0.64
     Chriftian
    0.64
     ―――――
    0.64
    ^(@)
    0.62
     pleaſure
    0.60
     gainera
    0.60
     AssemblyCulture
    0.60
    Act Density 2.603%

    No Known Activations