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

    Neuronpedia

    INDEX
    Explanations

    expressions of negative sentiment or criticism

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

    basedencodedscanningsplittingProfile

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ChildScrollView
    -0.51
    providedIn
    -0.50
    enumii
    -0.50
    Diweddarwch
    -0.49
    -0.49
     snippetHide
    -0.48
    delwed
    -0.46
    hyrchwyd
    -0.45
    richTextPanel
    -0.45
    usercontent
    -0.45
    POSITIVE LOGITS
     Flame
    0.48
    munk
    0.48
     Griff
    0.48
     ་་
    0.47
    DEAL
    0.47
     Perfor
    0.47
     décor
    0.46
    Mun
    0.46
     Grape
    0.46
    coast
    0.45
    Act Density 0.151%

    No Known Activations