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

    Neuronpedia

    INDEX
    Explanations

    grammar

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ::::
    -0.07
    ermann
    -0.07
    rich
    -0.07
    rieb
    -0.06
     sensors
    -0.06
    ----
    -0.06
     і
    -0.06
     suicidal
    -0.06
    вся
    -0.06
    �게
    -0.06
    POSITIVE LOGITS
     Singleton
    0.07
     практически
    0.07
     ounce
    0.06
     Dollar
    0.06
     SMP
    0.06
     마지막
    0.06
    umsuz
    0.06
     ceny
    0.06
     tendr
    0.06
    صر
    0.06
    Act Density 0.021%

    No Known Activations