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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to scientific research and their implications

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

    causes to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.54
    wußt
    -0.36
    Parcelize
    -0.34
    hankelijk
    -0.34
    
    -0.33
     hvilket
    -0.32
     virtuel
    -0.32
     métiers
    -0.31
    wieś
    -0.31
    نجليز
    -0.30
    POSITIVE LOGITS
    +#+#
    0.69
     snippetHide
    0.65
    IntoConstraints
    0.60
     defStyleAttr
    0.58
     NSCoder
    0.53
    tagext
    0.52
     Meksiku
    0.51
    fjspx
    0.50
     ['./
    0.49
     defStyle
    0.49
    Act Density 0.162%

    No Known Activations