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

    Neuronpedia

    INDEX
    Explanations

    known

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     göster
    -0.06
    пня
    -0.06
    uess
    -0.06
    acer
    -0.06
     Sie
    -0.06
    (bytes
    -0.06
    classname
    -0.06
    .tap
    -0.06
    auge
    -0.06
     Entire
    -0.06
    POSITIVE LOGITS
     known
    0.17
    known
    0.14
    -known
    0.11
     Known
    0.11
     KN
    0.08
     unknown
    0.08
    Known
    0.08
     suspected
    0.07
    025
    0.07
     γνω
    0.07
    Act Density 0.036%

    No Known Activations