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

    Neuronpedia

    INDEX
    Explanations

    privacy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     слу
    -0.07
     एन
    -0.07
    ерів
    -0.07
    ятий
    -0.07
    ždy
    -0.07
     PROVID
    -0.07
     teaching
    -0.07
     Educ
    -0.06
     rodiny
    -0.06
    آن
    -0.06
    POSITIVE LOGITS
     Franz
    0.06
     oauth
    0.06
    Dimensions
    0.06
    mute
    0.06
    ]+'
    0.06
    nova
    0.06
    ('_
    0.05
    (""))↵
    0.05
     PRIMARY
    0.05
    icare
    0.05
    Act Density 0.007%

    No Known Activations