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

    Neuronpedia

    INDEX
    Explanations

    references to programming libraries or frameworks

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

    javascript file references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -1.02
     Италијани
    -0.80
     Signalez
    -0.77
    richTextPanel
    -0.76
    dafx
    -0.76
     Administrativna
    -0.75
    Tembelea
    -0.74
     linkovi
    -0.73
    ⓧ
    -0.72
     ProtoMessage
    -0.71
    POSITIVE LOGITS
     schia
    0.31
    こちらも
    0.31
    ึง
    0.29
     фона
    0.28
     novia
    0.27
     respectively
    0.27
     respectivamente
    0.27
     Seele
    0.26
     meanwhile
    0.26
    گر
    0.26
    Act Density 0.001%

    No Known Activations