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

    Neuronpedia

    INDEX
    Explanations

    specialized terminology related to scientific methodologies and their effectiveness in various applications

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

    use of tools for detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.68
    OGND
    -0.52
    󠁿
    -0.49
    ]--;
    -0.48
     purpoſe
    -0.46
    󠁣
    -0.46
     المعيارى
    -0.44
     himſelf
    -0.44
     OFDb
    -0.43
    ementara
    -0.43
    POSITIVE LOGITS
    ніципалі
    0.42
    ul
    0.37
    tools
    0.34
    ヌーピー
    0.34
     tools
    0.34
     technology
    0.34
    لينكات
    0.33
    xtext
    0.33
     nghiệm
    0.33
    umblebee
    0.32
    Act Density 0.428%

    No Known Activations