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

    Neuronpedia

    INDEX
    Explanations

    the use of slashes and tutorial references in documentation, likely indicating code structure or organization

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

    java, tutorial, mask

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isielt
    -0.49
     pasirink
    -0.44
     Italijani
    -0.43
     naudoti
    -0.42
    LookAnd
    -0.42
     apsau
    -0.40
    AsUp
    -0.40
     universelle
    -0.40
     république
    -0.40
    annelse
    -0.39
    POSITIVE LOGITS
    MemoryWarning
    0.56
    ContentLoaded
    0.56
    VersionUID
    0.55
    principalColumn
    0.55
    +#+#
    0.54
    GOTREF
    0.52
    原始内容存档于
    0.51
     nahilalakip
    0.51
    waitKey
    0.49
     ModelExpression
    0.47
    Act Density 0.001%

    No Known Activations