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

    Neuronpedia

    INDEX
    Explanations

    statistical terms and references to scientific methodologies

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

    scientific and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FUCKING
    -0.53
     fucking
    -0.49
     Fucking
    -0.49
    Fucking
    -0.47
    DataAnnotations
    -0.46
    ChildScrollView
    -0.46
    antMatchers
    -0.45
    underbrace
    -0.45
    ————————————————
    -0.44
    EndInit
    -0.44
    POSITIVE LOGITS
     препратки
    0.48
     ब्रेकडाउन
    0.42
    úsqueda
    0.41
     Shetterly
    0.40
     chẳng
    0.39
    Gweler
    0.39
     useAppContext
    0.39
    Izvori
    0.39
     跳转至
    0.39
    Legături
    0.38
    Act Density 0.280%

    No Known Activations