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

    Neuronpedia

    INDEX
    Explanations

    references to research documents and publication details

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

    `user` token sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.68
    сылкі
    -0.60
    WriteLiteral
    -0.59
    InSection
    -0.57
     مشين
    -0.55
     <<<<<<<<<<<<<<
    -0.54
    enterOuterAlt
    -0.53
    -0.53
    HostException
    -0.51
    ➌
    -0.51
    POSITIVE LOGITS
     Autorizaciones
    0.49
     dedicated
    0.44
    ngdoc
    0.43
    semibold
    0.38
    setSubject
    0.38
     devoted
    0.35
     Gesch
    0.35
    まれる
    0.33
     rechange
    0.33
     Beste
    0.33
    Act Density 0.002%

    No Known Activations