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

    Neuronpedia

    INDEX
    Explanations

    specific medical terms and metrics related to research findings

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

    Numbers, especially "0" or numbers followed by "million"

    np_acts-logits-general · gemini-2.0-flash

    numbers and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ']))
    -0.91
     }],
    -0.81
    }$​
    -0.77
    "]);
    -0.76
    }');
    -0.75
    })),
    -0.74
    }")]
    -0.73
    }';
    -0.72
    '))
    -0.72
    })).
    -0.72
    POSITIVE LOGITS
    0
    0.77
    #+#
    0.60
    s
    0.60
    tvguidetime
    0.59
    jména
    0.57
     portátiles
    0.56
    AndEndTag
    0.54
     gioca
    0.53
    SaveChanges
    0.52
     Cuth
    0.51
    Act Density 0.468%

    No Known Activations