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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values associated with data attributes

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

    Click here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſch
    -0.64
    enderror
    -0.62
     sumpay
    -0.61
     Italijani
    -0.59
    yntaxException
    -0.59
    Personendaten
    -0.59
    twimg
    -0.58
    autaire
    -0.57
    contentLoaded
    -0.57
    Ӕ
    -0.56
    POSITIVE LOGITS
    Clik
    0.34
    spli
    0.33
     Intended
    0.33
    colgante
    0.31
    CAND
    0.30
    FLAGS
    0.30
    texttt
    0.29
    chaleco
    0.29
     "
    0.28
     Foire
    0.28
    Act Density 0.021%

    No Known Activations