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

    Neuronpedia

    INDEX
    Explanations

    positive descriptors related to quality and excellence

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

    positive adjectives followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eşofman
    -0.40
    CrossRef
    -0.38
    AddHtmlAttribute
    -0.35
    хьтан
    -0.35
    WriteTagHelper
    -0.35
     calendriers
    -0.35
    sweise
    -0.34
     ziekte
    -0.33
     Verhältnisse
    -0.33
    ViewImports
    -0.33
    POSITIVE LOGITS
    醐
    0.49
     beauties
    0.48
    posedge
    0.48
    mont
    0.47
    美味し
    0.47
    mejores
    0.47
     positives
    0.46
    ニュ
    0.45
    大神
    0.44
    AxisAlignment
    0.44
    Act Density 0.015%

    No Known Activations