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

    Neuronpedia

    INDEX
    Explanations

    the word "before" or "after"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ÑģÑĤи
    -0.07
    stown
    -0.07
    ãĥ¼ãĥĭ
    -0.06
     bag
    -0.06
    etto
    -0.06
    abwe
    -0.06
    MLE
    -0.06
    [*
    -0.06
    LD
    -0.06
     far
    -0.06
    POSITIVE LOGITS
    mentioned
    0.08
    acious
    0.07
    noon
    0.07
    éĶĭ
    0.06
    olate
    0.06
    cestor
    0.06
     Constantin
    0.06
    tors
    0.06
    uintptr
    0.06
    tings
    0.06
    Act Density 0.014%

    No Known Activations