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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     собі
    -0.07
    ampled
    -0.07
     здесь
    -0.07
    録
    -0.07
    598
    -0.07
     тогда
    -0.06
    .raw
    -0.06
     kos
    -0.06
     devant
    -0.06
     days
    -0.06
    POSITIVE LOGITS
     signature
    0.07
     ReSharper
    0.07
     голова
    0.06
     Nuggets
    0.06
    (states
    0.06
     coff
    0.06
    *[
    0.06
    (FLAGS
    0.06
    getX
    0.06
    (hours
    0.06
    Act Density 0.021%

    No Known Activations