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

    Neuronpedia

    INDEX
    Explanations

    qualifications and conclusions

    oai_token-act-pair · gemini-2.0-flash

    alternatives and conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +#+#
    -1.45
     Efq
    -1.20
     moschino
    -1.13
    LookAnd
    -1.12
     myſelf
    -1.05
    MessageOf
    -1.05
    StructEnd
    -1.04
    UnusedPrivate
    -1.03
     Jefus
    -1.02
    bootstrapcdn
    -1.02
    POSITIVE LOGITS
    ↵↵
    0.79
    :
    0.75
    <eos>
    0.71
    ...
    0.61
     
    0.61
    ↵
    0.61
    ;
    0.60
     (
    0.60
    ,
    0.57
         
    0.56
    Act Density 1.820%

    No Known Activations