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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     productService
    -0.26
    PTS
    -0.25
    AFP
    -0.25
     reimburse
    -0.24
    ifo
    -0.24
    AMIL
    -0.23
    iefs
    -0.23
    +A
    -0.23
    ModelProperty
    -0.23
     Americans
    -0.23
    POSITIVE LOGITS
    èĩ£
    0.28
     suppl
    0.26
    asio
    0.26
    éķľå¤´
    0.26
    Scheduled
    0.25
    è¯ļ
    0.25
    ä¿İ
    0.25
    liner
    0.24
    oulos
    0.23
    .Types
    0.23
    Act Density 7.037%

    No Known Activations