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

    Neuronpedia

    INDEX
    Explanations

    HD

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crucial
    -0.06
    高速
    -0.06
    採
    -0.06
     deceit
    -0.06
     глав
    -0.06
    ?>
    -0.06
     mower
    -0.06
     Seam
    -0.06
    _THRESH
    -0.06
    -anchor
    -0.05
    POSITIVE LOGITS
     است
    0.07
     山
    0.07
    ENTION
    0.07
    olves
    0.06
    ивается
    0.06
     holland
    0.06
     ard
    0.06
    ognition
    0.06
    이트
    0.06
    دا
    0.06
    Act Density 0.000%

    No Known Activations