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

    Neuronpedia

    INDEX
    Explanations

    references to data, numerical values, or measurements related to experimental results

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

    Code, programming, and software related text

    np_acts-logits-general · gemini-2.0-flash

    Impl test, DM groups, Repeated StringField

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.67
    <eos>
    -0.66
    ;
    -0.63
    ,
    -0.58
    :
    -0.52
    ↵↵
    -0.51
    ]
    -0.49
     -
    -0.47
     ;
    -0.45
     for
    -0.45
    POSITIVE LOGITS
    AsUp
    0.96
    adaptiveStyles
    0.93
     purpoſe
    0.92
     myſelf
    0.92
     ſeveral
    0.90
    脚注の使い方
    0.90
     nakalista
    0.88
    ########.
    0.88
     ་་
    0.88
     Reſ
    0.88
    Act Density 0.531%

    No Known Activations