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

    Neuronpedia

    INDEX
    Explanations

    FITNESS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .eye
    -0.07
     lacks
    -0.06
     reproduced
    -0.06
     Müdür
    -0.06
    جيل
    -0.06
    vik
    -0.06
    /im
    -0.06
    โลก
    -0.06
    .elapsed
    -0.06
     broken
    -0.06
    POSITIVE LOGITS
    ┘
    0.06
    umping
    0.06
    othermal
    0.06
     (=
    0.06
    arsers
    0.06
     Jerome
    0.06
     」
    0.06
     configurations
    0.06
     Mul
    0.06
     publication
    0.06
    Act Density 0.000%

    No Known Activations