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

    Neuronpedia

    INDEX
    Explanations

    syntactic structures related to mathematical expressions and programming logic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical expressions with variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Santa
    -0.42
     E
    -0.39
    Gentle
    -0.37
     Con
    -0.36
     Ne
    -0.36
     Bri
    -0.36
    ym
    -0.35
     San
    -0.35
     Fe
    -0.35
     
    -0.35
    POSITIVE LOGITS
    хьтан
    0.63
     виправивши
    0.62
     Италијани
    0.61
    Espèce
    0.55
    তথ্যসূত্র
    0.54
    embatan
    0.54
     INTERESAR
    0.54
     nakalista
    0.52
    sizeCache
    0.52
     increí
    0.52
    Act Density 0.001%

    No Known Activations