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

    Neuronpedia

    INDEX
    Explanations

    stratified random sampling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lifecycle
    -0.08
    ">&
    -0.08
     sehe
    -0.07
    Unicode
    -0.07
     vis
    -0.07
     kone
    -0.07
     zien
    -0.07
     кноп
    -0.07
     바이
    -0.07
     Vanity
    -0.07
    POSITIVE LOGITS
    .random
    0.09
    .randint
    0.09
     distributing
    0.08
     ruling
    0.08
     pity
    0.08
     Algar
    0.08
     interes
    0.08
     impartial
    0.08
     distribute
    0.08
     accordance
    0.08
    Act Density 0.008%

    No Known Activations