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

    Neuronpedia

    INDEX
    Explanations

    y

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     cenu
    -0.06
     TMP
    -0.06
     withstand
    -0.06
    truck
    -0.06
     silicone
    -0.06
     digging
    -0.06
    Disposable
    -0.06
     sufficient
    -0.06
     fö
    -0.06
    POSITIVE LOGITS
    처
    0.08
    Aff
    0.07
    Howard
    0.07
     diffic
    0.07
    _associ
    0.07
     Latter
    0.07
    (objects
    0.07
    typedef
    0.06
    Miller
    0.06
    :not
    0.06
    Act Density 0.002%

    No Known Activations