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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to scientific research and job postings

    oai_token-act-pair · gemini-2.0-flash

    Academic/technical snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ad
    -0.96
     An
    -0.95
     Am
    -0.92
     Ap
    -0.91
     Av
    -0.91
     Ax
    -0.91
     Ab
    -0.90
     Ak
    -0.88
     Ac
    -0.88
     Ag
    -0.87
    POSITIVE LOGITS
    humanité
    0.59
    empereur
    0.52
    StoryboardSegue
    0.51
     صوتيه
    0.48
    assemblée
    0.46
    humidité
    0.45
     ProtoMessage
    0.44
    hygiène
    0.44
    anniversaire
    0.44
    RetentionPolicy
    0.43
    Act Density 51.459%

    No Known Activations