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

    Neuronpedia

    INDEX
    Explanations

    instances of social commentary or criticism

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

    start of turn user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    clerView
    -0.37
     câbles
    -0.36
     directa
    -0.35
     anillos
    -0.33
    riwal
    -0.32
     hombro
    -0.32
     esperienza
    -0.32
     cabezas
    -0.31
     direto
    -0.30
    屋根
    -0.30
    POSITIVE LOGITS
    providedIn
    0.65
     AssemblyProduct
    0.65
    enderror
    0.64
    dailymail
    0.63
     comuniques
    0.51
    UALA
    0.50
     *)__
    0.50
    createCanvas
    0.50
     <<<<<<<<<<<<<<
    0.49
    UnitTesting
    0.47
    Act Density 0.012%

    No Known Activations