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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and special characters in documents

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

    Code snippets or file paths

    np_acts-logits-general · gemini-2.0-flash

    code, arabic, pdf files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     חיצוניים
    -0.79
    AndEndTag
    -0.74
    DebuggerStep
    -0.72
     rospy
    -0.69
     nakalista
    -0.66
     дописавши
    -0.65
    ArgsConstructor
    -0.65
    новниш
    -0.64
    kháu
    -0.63
     DialogInterface
    -0.62
    POSITIVE LOGITS
     devenus
    0.57
     prisonniers
    0.56
     complètes
    0.56
     démocr
    0.56
     sélectionnés
    0.55
     armées
    0.55
     spécialisé
    0.53
     dédi
    0.53
     européennes
    0.53
     supérieurs
    0.52
    Act Density 0.001%

    No Known Activations