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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "lol" and numerical or mathematical expressions

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

    code or math ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -1.13
    rungsseite
    -0.99
    )))),
    -0.98
     CreateTagHelper
    -0.97
    )))));
    -0.93
    ")));
    -0.91
     المعيارى
    -0.89
    "])
    -0.86
    }))
    -0.85
    "]));
    -0.84
    POSITIVE LOGITS
     (
    0.53
    .
    0.51
     alimentaria
    0.48
     olacak
    0.47
    )
    0.47
     rodillas
    0.46
    “
    0.45
     judiciaire
    0.44
    (
    0.44
     femenina
    0.44
    Act Density 0.100%

    No Known Activations