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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to analysis and evaluation processes

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

    Items in a numbered list

    np_acts-logits-general · gemini-2.0-flash

    application form preparation approvals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.90
    providedIn
    -0.82
    "!
    -0.77
    }'.
    -0.77
    __":
    -0.75
    ”!
    -0.74
    }".
    -0.74
    '!
    -0.71
     CURIAM
    -0.70
    )!
    -0.69
    POSITIVE LOGITS
     ;
    0.81
    　・
    0.78
    ;</
    0.77
    ;
    0.74
    二是
    0.72
    」、「
    0.71
    ;<
    0.70
     ②
    0.70
                                   
    0.70
             
    0.70
    Act Density 0.853%

    No Known Activations