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

    Neuronpedia

    INDEX
    Explanations

    references to the name "Mr." followed by a name or title in various contexts

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

    "Mr." followed by a name

    np_acts-logits-general · gemini-2.0-flash

    Mr. followed by a name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Step
    -0.46
    //
    -0.40
    خ
    -0.40
    ;
    -0.40
    (
    -0.40
    ,
    -0.39
    ửa
    -0.39
    ()
    -0.38
     Strafe
    -0.38
     baik
    -0.38
    POSITIVE LOGITS
     protoimpl
    0.95
     виправивши
    0.91
    exitRule
    0.91
    Tikang
    0.90
    fjspx
    0.88
    ModelSerializer
    0.88
    sizeCache
    0.85
    ⓧ
    0.83
     препратки
    0.82
     архивлан
    0.82
    Act Density 0.073%

    No Known Activations