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

    Neuronpedia

    INDEX
    Explanations

    technical jargon and variables associated with programming or data analysis

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

    setting parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.41
     “
    -0.39
     a
    -0.35
     bas
    -0.35
    van
    -0.34
     exact
    -0.34
    <em>
    -0.34
     un
    -0.34
     "
    -0.33
    exact
    -0.33
    POSITIVE LOGITS
     المعيارى
    0.75
    transQ
    0.73
     BoxFit
    0.73
     wireType
    0.67
     desmotivaciones
    0.63
    脚注の使い方
    0.60
    ########.
    0.60
    دانشنامهٔ
    0.60
    tangentMode
    0.59
    évaluateur
    0.59
    Act Density 0.205%

    No Known Activations