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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    structured approaches to presenting information, particularly in a formal or academic context.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    iyim
    -0.07
    验
    -0.07
    sus
    -0.07
     ringing
    -0.06
     امید
    -0.06
     pylint
    -0.06
    etzt
    -0.06
     �
    -0.06
    ى
    -0.06
     hlub
    -0.06
    POSITIVE LOGITS
    那个
    0.07
    Ghost
    0.07
    ffa
    0.07
    Actually
    0.07
    Blank
    0.07
     numOf
    0.07
     name
    0.06
    _util
    0.06
     award
    0.06
    seud
    0.06
    Act Density 0.016%

    No Known Activations