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

    Neuronpedia

    INDEX
    Explanations

    cautionary language regarding future predictions and risks

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

    obligation to update

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Che
    -0.43
     terrors
    -0.42
     insane
    -0.41
     tips
    -0.40
     tones
    -0.38
    Che
    -0.37
    ad
    -0.37
    g
    -0.36
     clapped
    -0.36
    che
    -0.36
    POSITIVE LOGITS
     pleaſure
    0.60
    帖最后由
    0.57
    ChildScrollView
    0.56
    httphttps
    0.55
    GTCX
    0.54
    rungsseite
    0.50
     Infórmanos
    0.50
    AndEndTag
    0.49
     poffible
    0.49
     становника
    0.48
    Act Density 0.013%

    No Known Activations