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

    Neuronpedia

    INDEX
    Explanations

    animated

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Joseph
    -0.06
     reluctantly
    -0.06
     Ter
    -0.06
    Rect
    -0.06
     Фран
    -0.06
    _AREA
    -0.06
    'ét
    -0.06
     constructed
    -0.06
     penalties
    -0.06
     Bayesian
    -0.06
    POSITIVE LOGITS
    (PyObject
    0.08
    那个
    0.07
    ("""
    0.07
    ποιη
    0.07
     �
    0.07
     saldo
    0.07
     ---↵
    0.07
    >(),
    0.06
     बच
    0.06
     upbeat
    0.06
    Act Density 0.004%

    No Known Activations