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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash

    text related to numerical rounding and decimal places.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    encoded
    -0.07
     yapan
    -0.07
    نتاج
    -0.07
     hasil
    -0.07
     Marc
    -0.06
     genel
    -0.06
    ुआ
    -0.06
    BOOT
    -0.06
     coeff
    -0.06
    -legged
    -0.06
    POSITIVE LOGITS
     răng
    0.07
     ”
    0.06
    لت
    0.06
    .tb
    0.06
     HQ
    0.06
     Caribbean
    0.06
    placements
    0.06
     ranging
    0.06
    ば
    0.06
    ?↵↵↵↵
    0.06
    Act Density 0.001%

    No Known Activations