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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ہوئی
    -0.09
    .criteria
    -0.09
    criteria
    -0.09
     stained
    -0.08
    .spacing
    -0.08
     consac
    -0.08
    visual
    -0.08
    مالية
    -0.08
     embodiment
    -0.08
     radiant
    -0.08
    POSITIVE LOGITS
     значения
    0.09
    $value
    0.09
     value
    0.09
     values
    0.08
     compute
    0.08
    -value
    0.08
     predict
    0.08
    Value
    0.08
     predictions
    0.08
     vanish
    0.08
    Act Density 0.079%

    No Known Activations