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

    Neuronpedia

    INDEX
    Explanations

    the prefix "poly"

    oai_token-act-pair · gemini-2.0-flash

    poly

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zelt
    -0.52
     best
    -0.52
    ientí
    -0.49
    knex
    -0.49
    ANCY
    -0.49
     more
    -0.48
    stoß
    -0.47
     da
    -0.47
    tikai
    -0.47
    vorg
    -0.47
    POSITIVE LOGITS
    \{\\
    0.81
     الحره
    0.77
    AnchorStyles
    0.66
    ])));
    0.58
    ConstraintMaker
    0.58
     esternos
    0.57
    tagHelperRunner
    0.57
    CloseOperation
    0.56
     gddr
    0.55
     wireType
    0.55
    Act Density 0.578%

    No Known Activations