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

    Neuronpedia

    INDEX
    Explanations

    references to the 21st century

    oai_token-act-pair · gemini-2.0-flash

    1 or 0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rd
    -1.41
    RD
    -1.13
     rd
    -1.09
     RD
    -1.01
    rds
    -0.94
    Personendaten
    -0.92
    MessageTagHelper
    -0.83
    rdi
    -0.80
    Rd
    -0.76
    tagHelperRunner
    -0.74
    POSITIVE LOGITS
    st
    1.00
    ST
    0.76
     st
    0.76
    St
    0.65
     St
    0.64
     ST
    0.61
     sti
    0.50
    sti
    0.50
     Stur
    0.49
    stt
    0.49
    Act Density 1.494%

    No Known Activations