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

    Neuronpedia

    INDEX
    Explanations

    Physics/math writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prediction
    -0.08
    퓨
    -0.07
    龙
    -0.07
    ňování
    -0.07
    、“
    -0.07
     الكتاب
    -0.07
     pays
    -0.06
    ZY
    -0.06
     otro
    -0.06
     yesterday
    -0.06
    POSITIVE LOGITS
    ็ต
    0.07
     recv
    0.07
    reements
    0.07
    ]+$
    0.06
     Strauss
    0.06
     succ
    0.06
    ***/↵
    0.06
     Sext
    0.06
     Gear
    0.06
    Voice
    0.06
    Act Density 0.001%

    No Known Activations