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

    Neuronpedia

    INDEX
    Explanations

    variations and formats related to data structures

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

    programming keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.68
    GraphicsUnit
    -0.62
     Comprometido
    -0.60
     архивлан
    -0.59
    verwijspagina
    -0.57
    ंदीखरीदारी
    -0.57
    +#+#
    -0.57
     defaultstate
    -0.56
     ExecuteAsync
    -0.56
     Bewußt
    -0.55
    POSITIVE LOGITS
     Imm
    0.53
    ssm
    0.51
    sam
    0.49
    Slip
    0.48
     affair
    0.48
     Slip
    0.48
     SIS
    0.47
    SEC
    0.47
    Dav
    0.47
    enf
    0.47
    Act Density 0.183%

    No Known Activations