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

    Neuronpedia

    INDEX
    Explanations

    warehouse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    increment
    -0.08
     pyl
    -0.07
     penn
    -0.07
    بير
    -0.07
     típ
    -0.07
     ions
    -0.07
     magnitude
    -0.07
     scaling
    -0.07
     provincias
    -0.07
    QUIRED
    -0.07
    POSITIVE LOGITS
     secluded
    0.11
     fenced
    0.09
     спр
    0.09
     chứa
    0.08
     tranquille
    0.08
    ेरी
    0.08
    FB
    0.07
     containing
    0.07
     deserted
    0.07
     tranquila
    0.07
    Act Density 0.041%

    No Known Activations