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

    Neuronpedia

    INDEX
    Explanations

    Refuting mathematical statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Thank
    -0.09
    Delay
    -0.08
    Detector
    -0.08
     Thank
    -0.08
    Detection
    -0.08
     פשוט
    -0.08
     letzte
    -0.08
    Доб
    -0.07
    Soft
    -0.07
     Detection
    -0.07
    POSITIVE LOGITS
    strict
    0.09
     strict
    0.09
     stringent
    0.09
     toro
    0.08
    ুৱ
    0.08
    (strict
    0.08
     χώρο
    0.08
     restrict
    0.08
     stric
    0.08
     contradictory
    0.08
    Act Density 0.107%

    No Known Activations