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

    Neuronpedia

    INDEX
    Explanations

    two

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    世紀
    -0.06
    浅
    -0.06
     допомаг
    -0.06
    �
    -0.06
     Eyes
    -0.06
     招
    -0.06
     EXPER
    -0.06
     onemoc
    -0.06
    ũi
    -0.06
     شمال
    -0.06
    POSITIVE LOGITS
     Meditation
    0.07
    toHaveBeenCalled
    0.07
    [in
    0.06
    」↵↵
    0.06
    "};↵↵
    0.06
    _manager
    0.06
    nop
    0.06
     stemmed
    0.06
    raith
    0.06
     sevent
    0.06
    Act Density 0.008%

    No Known Activations