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

    Neuronpedia

    INDEX
    Explanations

    references to heads or bodies in certain locations

    oai_token-act-pair · gemini-2.0-flash

    head

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "..\..\..\
    -0.73
     Италијани
    -0.68
    EndInit
    -0.68
    IntoConstraints
    -0.64
    tigungs
    -0.64
    uitable
    -0.64
     تضيفلها
    -0.63
    StructEnd
    -0.58
    UVWXYZ
    -0.58
     يتيمه
    -0.57
    POSITIVE LOGITS
    ölkerung
    0.61
     AssemblyCulture
    0.59
    Slf
    0.48
    |}{
    0.48
    ),”
    0.47
     Référence
    0.47
    principalTable
    0.46
    agg
    0.45
    avadoc
    0.44
     jaunes
    0.43
    Act Density 1.597%

    No Known Activations