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

    Neuronpedia

    INDEX
    Explanations

    initialisms/abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Twig
    -0.44
     al
    -0.41
    RequestMapping
    -0.40
     ISNI
    -0.40
     quality
    -0.40
    ]=$
    -0.40
     fleste
    -0.39
    SourceChecksum
    -0.39
     “
    -0.37
     »
    -0.37
    POSITIVE LOGITS
     myſelf
    0.90
    Personendaten
    0.79
     HasFactory
    0.79
     Jefus
    0.75
     pleaſure
    0.75
    ErrUnexpectedEOF
    0.72
     whoſe
    0.72
    expandindo
    0.71
     houſe
    0.71
    ſelf
    0.70
    Act Density 0.028%

    No Known Activations