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

    Neuronpedia

    INDEX
    Explanations

    prepositions and related words indicating possession or location, along with references to official bodies or code structures.

    oai_token-act-pair · gemini-2.0-flash

    common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.78
    featureID
    -0.77
    PerformLayout
    -0.75
     betweenstory
    -0.69
     ſy
    -0.65
     صوتيه
    -0.65
     nahilalakip
    -0.65
     Comprometido
    -0.65
    <bos>
    -0.65
     Shakspeare
    -0.64
    POSITIVE LOGITS
    handelt
    0.51
    tighet
    0.51
    pekte
    0.50
     MethodInfo
    0.48
    quilo
    0.47
    secutions
    0.47
     torchvision
    0.47
    )−
    0.47
    insics
    0.45
    '--
    0.45
    Act Density 2.276%

    No Known Activations