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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to user interactions and potential outcomes

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

    might affect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lindberg
    -0.39
    te
    -0.39
    δας
    -0.39
    Rüyada
    -0.39
    su
    -0.39
     Schulze
    -0.38
     Vogt
    -0.36
     Johansen
    -0.36
    gu
    -0.35
     Donahue
    -0.35
    POSITIVE LOGITS
    enderror
    0.91
     nahilalakip
    0.74
    tagHelperRunner
    0.71
    bcryptjs
    0.67
    ſelves
    0.67
     '\\;'
    0.60
     &___
    0.59
     lenker
    0.58
    ftagPool
    0.58
    ſelf
    0.57
    Act Density 0.000%

    No Known Activations