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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    목
    -0.08
     Sc
    -0.07
    ENDER
    -0.07
    وقف
    -0.07
    bower
    -0.07
     ladder
    -0.07
     рук
    -0.06
    meleri
    -0.06
     그래서
    -0.06
    PackageManager
    -0.06
    POSITIVE LOGITS
     поскольку
    0.07
     ),
↵
    0.07
    ivant
    0.06
    Advertis
    0.06
     Eastern
    0.06
    write
    0.06
    _components
    0.06
    lla
    0.06
    	ep
    0.06
     nephew
    0.06
    Act Density 0.014%

    No Known Activations