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

    Neuronpedia

    INDEX
    Explanations

    Expression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heroic
    -0.07
     او
    -0.07
    akov
    -0.07
    .hardware
    -0.06
    teri
    -0.06
     giai
    -0.06
    омет
    -0.06
     analysis
    -0.06
     documento
    -0.06
     invading
    -0.06
    POSITIVE LOGITS
     renting
    0.06
    <stdlib
    0.06
    ันน
    0.06
    student
    0.06
    destination
    0.06
    	initial
    0.06
    achers
    0.06
    .surname
    0.06
     ";↵↵
    0.06
     động
    0.06
    Act Density 0.002%

    No Known Activations