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

    Neuronpedia

    INDEX
    Explanations

    references to clickable links and safety ratings in documents

    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
     betweenstory
    -0.97
    aarrggbb
    -0.97
     queſta
    -0.87
     otomatig
    -0.86
     للمعارف
    -0.84
    BibitemShut
    -0.79
    niſſe
    -0.79
    ſſung
    -0.79
     imagui
    -0.79
    ロウィン
    -0.79
    POSITIVE LOGITS
    In
    0.36
    The
    0.35
    With
    0.34
    For
    0.34
    No
    0.33
    1
    0.33
    2
    0.32
     $^{\
    0.32
    ỏa
    0.31
    :
    0.31
    Act Density 0.031%

    No Known Activations