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

    Neuronpedia

    INDEX
    Explanations

    numbers, percentages, and basic adjectives

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gouvernements
    -0.72
     négociations
    -0.63
     engraçadas
    -0.63
     genoux
    -0.63
     chrétiens
    -0.63
     nuages
    -0.60
     industriels
    -0.60
     funcionales
    -0.58
     dirigeants
    -0.57
     défauts
    -0.56
    POSITIVE LOGITS
    SequentialGroup
    0.68
    Kaynakça
    0.60
    #+#
    0.59
    0.59
    tonode
    0.58
    IntoConstraints
    0.58
    protoimpl
    0.57
    __((
    0.56
     незавершена
    0.56
     <<<<<<<<<<<<<<
    0.56
    Act Density 11.879%

    No Known Activations