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

    Neuronpedia

    INDEX
    Explanations

    leaders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بالفعل
    -0.09
    _activation
    -0.08
     ripe
    -0.08
     ACTIV
    -0.08
     rife
    -0.08
     DRM
    -0.08
    _case
    -0.08
     karbon
    -0.08
    _noise
    -0.08
     મિત્ર
    -0.08
    POSITIVE LOGITS
     elected
    0.12
     appointed
    0.11
     holders
    0.10
    -appointed
    0.10
     whoever
    0.10
     encargado
    0.10
     chefs
    0.09
    职责
    0.09
    Responsibilities
    0.09
     नियुक्त
    0.09
    Act Density 0.048%

    No Known Activations