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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    していた
    -0.07
     volunteering
    -0.07
     اختصاص
    -0.06
     Appointment
    -0.06
    controller
    -0.06
     observer
    -0.06
    ernational
    -0.06
    шло
    -0.06
     undefined
    -0.06
     satisfaction
    -0.06
    POSITIVE LOGITS
     Thin
    0.06
     Finn
    0.06
    leader
    0.06
    .align
    0.06
    ологии
    0.06
    romatic
    0.06
    .Shared
    0.06
    acial
    0.06
     painful
    0.06
    rol
    0.05
    Act Density 0.015%

    No Known Activations