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

    Neuronpedia

    INDEX
    Explanations

    code snippets and parameter names

    oai_token-act-pair · gemini-2.0-flash

    string values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.70
    (!__
    -0.69
    }),
    -0.68
    "]),
    -0.64
     gynhyrchwyd
    -0.64
     <=",
    -0.54
    }])
    -0.52
    ']),
    -0.51
    rungsseite
    -0.49
    '}),
    -0.49
    POSITIVE LOGITS
     Efq
    0.52
     ſeveral
    0.52
     iſt
    0.47
     Jefus
    0.47
    Cursors
    0.47
     Chriftian
    0.47
     referenties
    0.46
     ſche
    0.46
     ſever
    0.45
    rachtet
    0.45
    Act Density 0.346%

    No Known Activations