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

    Neuronpedia

    INDEX
    Explanations

    requests for assistance or information on technical topics

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

    Text with informal abbreviations and punctuation

    np_acts-logits-general · gemini-2.0-flash

    asking for help or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;-)
    -0.56
    })));
    -0.55
    ‐
    -0.51
    :-)
    -0.51
    ｝
    -0.49
     denomina
    -0.48
     …..
    -0.47
    omiast
    -0.47
    %}
    -0.47
    #}
    -0.46
    POSITIVE LOGITS
     goddamn
    1.20
     idk
    1.17
     lmao
    1.01
     fuckin
    1.00
    idk
    1.00
     fucking
    0.99
     Idk
    0.99
     FUCKING
    0.97
     iirc
    0.94
     tbh
    0.93
    Act Density 0.824%

    No Known Activations