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

    Neuronpedia

    INDEX
    Explanations

    code snippets, URLs, questions, and business names

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.80
    ſelf
    -0.75
     houſe
    -0.74
    ſelves
    -0.73
     purpoſe
    -0.72
     pleaſure
    -0.69
     myſelf
    -0.68
     ſte
    -0.68
     itſelf
    -0.68
    ELTS
    -0.66
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.47
    parametrize
    0.45
    principalColumn
    0.40
    <bos>
    0.40
     makeStyles
    0.39
    WriteBarrier
    0.39
    exitRule
    0.39
    endalikan
    0.37
    ArgsConstructor
    0.36
    marshal
    0.36
    Act Density 0.420%

    No Known Activations