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

    Neuronpedia

    INDEX
    Explanations

    anti

    np_max-act · gemini-2.0-flash

    This neuron activates on Cyrillic-script tokens, effectively detecting Russian text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Smith
    -0.08
    439
    -0.07
    41
    -0.07
    497
    -0.07
    443
    -0.07
     practitioner
    -0.07
    44
    -0.07
     Femin
    -0.07
    ucceeded
    -0.07
    LU
    -0.07
    POSITIVE LOGITS
    &&(
    0.07
     바람
    0.07
     Мон
    0.07
     abbrev
    0.06
    一个
    0.06
     Κατηγορία
    0.06
    Conexion
    0.06
     cardboard
    0.06
    .Lines
    0.06
     '.';↵
    0.06
    Act Density 0.223%

    No Known Activations