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

    Neuronpedia

    INDEX
    Explanations

    Bureau of domain names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NotBlank
    1.04
     Trường
    0.97
     числе
    0.96
     фунда
    0.93
    دو
    0.93
    BLACKLIST
    0.91
    Tween
    0.90
    ング
    0.90
    نامه
    0.90
    ud
    0.89
    POSITIVE LOGITS
    &=\
    1.04
    iffent
    1.01
     statistics
    0.99
     discernment
    0.98
     inch
    0.97
    शाही
    0.96
    кр
    0.96
    砳
    0.94
    jski
    0.92
    istischen
    0.92
    Act Density 0.003%

    No Known Activations