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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     locally
    -0.07
    ера
    -0.07
    Annotation
    -0.07
     expressly
    -0.07
    式的
    -0.06
     بلا
    -0.06
    出て
    -0.06
    teenth
    -0.06
     #'
    -0.06
     nước
    -0.06
    POSITIVE LOGITS
    -com
    0.07
    oplayer
    0.07
    Sept
    0.07
     בבית
    0.07
    -news
    0.07
     Impossible
    0.07
    hiba
    0.07
    -alert
    0.07
     масс
    0.07
    (New
    0.06
    Act Density 0.025%

    No Known Activations