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

    Neuronpedia

    INDEX
    Explanations

    lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DialogTitle
    -0.07
     manten
    -0.07
     kvinne
    -0.07
    рест
    -0.07
     heads
    -0.07
    tokenizer
    -0.07
    41
    -0.06
     Cron
    -0.06
    .print
    -0.06
     cakes
    -0.06
    POSITIVE LOGITS
    χία
    0.07
     PreparedStatement
    0.06
    agem
    0.06
    DDL
    0.06
     зазнач
    0.06
     oldu
    0.06
     singular
    0.06
    iards
    0.06
     veriyor
    0.06
    asion
    0.06
    Act Density 0.058%

    No Known Activations