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

    Neuronpedia

    INDEX
    Explanations

    specific coding or formatting syntax used in programming

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

    Code, tables, and technical documentation

    np_acts-logits-general · gemini-2.0-flash

    List items, titles, sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    itudinal
    -0.45
     стаття
    -0.45
    Aktualisiert
    -0.44
    $$
    -0.43
    $.
    -0.41
    transQ
    -0.41
    erapeu
    -0.40
     visuel
    -0.40
    -_-
    -0.39
    drawal
    -0.39
    POSITIVE LOGITS
    <eos>
    1.17
    MigrationBuilder
    0.72
    addContainerGap
    0.67
    }}}}
    0.66
    }}
    0.65
    "]}
    0.65
    ```
    0.65
     }}}
    0.64
    "}
    0.64
    ĭ
    0.63
    Act Density 0.134%

    No Known Activations