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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of surplus

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

    surplus bound and extraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fromCharCode
    -0.43
     FetchType
    -0.43
    ocardio
    -0.41
    choenen
    -0.39
    makedirs
    -0.39
     Naciones
    -0.38
     nail
    -0.38
     Độ
    -0.37
    Revenir
    -0.37
    #[
    -0.36
    POSITIVE LOGITS
     surplus
    2.08
     Surplus
    2.06
     surpluses
    1.66
     surpl
    0.79
    ficit
    0.76
    Sur
    0.75
     superflu
    0.74
     superfluous
    0.73
    sur
    0.72
     SUR
    0.71
    Act Density 0.005%

    No Known Activations