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

    Neuronpedia

    INDEX
    Explanations

    JSON formatted data

    oai_token-act-pair · gemini-2.0-flash

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bassi
    -0.56
    relenting
    -0.53
     defStyleAttr
    -0.52
     Pelleg
    -0.51
     charge
    -0.51
     ErrIntOverflow
    -0.51
     CHAIR
    -0.50
     cess
    -0.50
    cela
    -0.50
    nsan
    -0.50
    POSITIVE LOGITS
    <bos>
    2.66
    #
    0.77
     Савезне
    0.71
    //
    0.71
    contentLoaded
    0.60
    Personendaten
    0.60
    脚注の使い方
    0.59
     estimés
    0.58
    __':
    0.57
    OGND
    0.56
    Act Density 0.553%

    No Known Activations