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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing positivity or high praise

    oai_token-act-pair · gemini-2.0-flash

    positive comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    artig
    -0.63
    ppets
    -0.53
    ranton
    -0.48
    hpur
    -0.48
     ThemeData
    -0.48
     betekenis
    -0.46
     &___
    -0.46
    ul
    -0.46
    yanka
    -0.44
    protoimpl
    -0.43
    POSITIVE LOGITS
    IsContent
    0.63
    archiviato
    0.56
     CURIAM
    0.56
    tał
    0.54
    InjectAttribute
    0.54
    ngdoc
    0.53
    pexpr
    0.52
    BASEPATH
    0.51
    stdc
    0.49
    ientôt
    0.49
    Act Density 1.468%

    No Known Activations