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

    Neuronpedia

    INDEX
    Explanations

    words related to software programs and/or accredited academic departments

    oai_token-act-pair · gemini-2.0-flash

    program

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.88
     مشين
    -0.86
    IVEREF
    -0.83
    AndEndTag
    -0.82
    numerusform
    -0.79
    astify
    -0.76
    setVerticalGroup
    -0.75
    StructEnd
    -0.75
    basicConfig
    -0.75
    AxisAlignment
    -0.73
    POSITIVE LOGITS
    medes
    0.47
    med
    0.41
    cesis
    0.40
    odan
    0.39
    mes
    0.39
    yente
    0.38
    τέ
    0.38
    ming
    0.37
    MING
    0.37
     ус
    0.36
    Act Density 3.853%

    No Known Activations