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

    Neuronpedia

    INDEX
    Explanations

    code snippets with the word "using System" and periods or semicolons

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beginnetje
    -0.89
     المعيارى
    -0.84
    bewerken
    -0.79
    OGND
    -0.77
    featureID
    -0.75
     betweenstory
    -0.75
     itſelf
    -0.75
    +#+#
    -0.65
     myſelf
    -0.63
    adpleegd
    -0.62
    POSITIVE LOGITS
     U
    0.60
     she
    0.57
    thol
    0.55
    tention
    0.54
    beri
    0.53
    áv
    0.52
     ke
    0.52
     K
    0.52
     Hanks
    0.51
     N
    0.50
    Act Density 0.146%

    No Known Activations