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

    Neuronpedia

    INDEX
    Explanations

    US

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     серед
    -0.07
    .Static
    -0.06
     moy
    -0.06
    圈
    -0.06
     growers
    -0.06
     MACHINE
    -0.06
     Alla
    -0.06
    .constraints
    -0.06
    hem
    -0.06
    ROM
    -0.06
    POSITIVE LOGITS
    -being
    0.07
    沒有
    0.07
    成为
    0.07
    0.06
    臺
    0.06
     inadvertently
    0.06
     slamming
    0.06
    ♪
    0.06
    urope
    0.06
    FFFFFF
    0.06
    Act Density 0.005%

    No Known Activations