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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Independ
    -0.07
    เท
    -0.07
     Craw
    -0.06
    704
    -0.06
    _related
    -0.06
    uye
    -0.06
    .booking
    -0.06
    ेह
    -0.06
    nard
    -0.06
    Chief
    -0.06
    POSITIVE LOGITS
    	cuda
    0.07
    /black
    0.07
    σει
    0.06
    regs
    0.06
     golden
    0.06
    察
    0.06
    Registry
    0.06
    连接
    0.06
     lucky
    0.06
    .Keyboard
    0.06
    Act Density 0.000%

    No Known Activations