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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chio
    -0.07
     Mey
    -0.07
    ]='\
    -0.06
    œur
    -0.06
    wow
    -0.06
     amassed
    -0.06
    EPROM
    -0.06
     норм
    -0.06
     그냥
    -0.06
     interchangeable
    -0.06
    POSITIVE LOGITS
    _ng
    0.08
    /l
    0.08
    /r
    0.07
    /y
    0.07
    storms
    0.07
    (dst
    0.07
    >',↵
    0.07
    DEV
    0.07
     Twist
    0.07
    /d
    0.06
    Act Density 0.000%

    No Known Activations