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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical expressions and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Letters used as variables or labels

    np_acts-logits-general · gemini-2.0-flash

    variables and letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.66
    ]));
    -0.57
    }))
    -0.55
    ]))
    -0.54
    })));
    -0.54
    "]));
    -0.50
     AssemblyCulture
    -0.50
    ])));
    -0.48
    ssd
    -0.47
     Ss
    -0.47
    POSITIVE LOGITS
     j
    0.67
    unknownFields
    0.63
     k
    0.61
    j
    0.59
    WithIOException
    0.59
     K
    0.54
    J
    0.53
    ConstraintMaker
    0.52
    K
    0.52
    jn
    0.52
    Act Density 1.034%

    No Known Activations