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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue and quotation marks

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

    "conflict" or "influence"

    np_acts-logits-general · gemini-2.0-flash

    influence of deprivation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )");
    -0.60
    }*/
    -0.60
    )*/
    -0.60
    });*/
    -0.59
    */;
    -0.58
    WithMany
    -0.57
    ")}
    -0.56
    --*/
    -0.55
    )";
    -0.55
    })*/
    -0.54
    POSITIVE LOGITS
     للمعارف
    0.67
     <=",
    0.62
     peix
    0.61
    msgTypes
    0.61
     esternos
    0.58
    Meanwhile
    0.56
     Meanwhile
    0.56
     recommandée
    0.55
    Simult
    0.55
     consultato
    0.54
    Act Density 0.032%

    No Known Activations