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

    Neuronpedia

    INDEX
    Explanations

    a combination of pronouns and prepositions

    oai_token-act-pair · gemini-2.0-flash

    them it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ArgsConstructor
    -0.68
    MessageOf
    -0.63
    /******/
    -0.58
    SourceChecksum
    -0.57
    ίδ
    -0.57
    ware
    -0.56
    yarnpkg
    -0.53
    EndContext
    -0.53
    scriptcase
    -0.53
     Injectable
    -0.52
    POSITIVE LOGITS
     ويكيپيديا
    0.50
     Majefty
    0.44
    ganz
    0.44
     հղումներ
    0.43
     lynx
    0.43
     rádio
    0.43
    fördert
    0.43
    derd
    0.43
    issionais
    0.43
     diría
    0.42
    Act Density 1.318%

    No Known Activations