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

    Neuronpedia

    INDEX
    Explanations

    saving time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    齐
    -0.08
     cockpit
    -0.08
    科
    -0.07
    ikations
    -0.07
     היח
    -0.07
    'end
    -0.07
     brave
    -0.07
     prek
    -0.07
     Brave
    -0.07
    ושא
    -0.07
    POSITIVE LOGITS
     evitando
    0.10
     tremendously
    0.09
     considerably
    0.09
     burocr
    0.09
     enormously
    0.09
     incurred
    0.09
     лиш
    0.09
     Needless
    0.09
     greatly
    0.09
     needless
    0.09
    Act Density 0.044%

    No Known Activations