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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ത്ഥ
    -0.08
     colorectal
    -0.08
    (||
    -0.07
     thereof
    -0.07
    עם
    -0.07
     Kolleg
    -0.07
    עת
    -0.07
    ථ
    -0.07
    223
    -0.07
    IIII
    -0.07
    POSITIVE LOGITS
     daughters
    0.08
     moko
    0.08
     وب
    0.08
     jub
    0.07
    gm
    0.07
     mitt
    0.07
     EObject
    0.07
     moons
    0.07
    ibat
    0.07
     Aya
    0.07
    Act Density 0.001%

    No Known Activations