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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    duck
    -0.07
    _large
    -0.06
     Friendship
    -0.06
     regulator
    -0.06
     Lar
    -0.06
     ultimately
    -0.06
     Panda
    -0.06
    )])↵
    -0.06
     Roberto
    -0.06
     metav
    -0.06
    POSITIVE LOGITS
    ,UnityEngine
    0.07
    	when
    0.07
    .inject
    0.06
    ička
    0.06
     �
    0.06
     trong
    0.06
    vě
    0.06
     διά
    0.06
    vla
    0.06
    díl
    0.06
    Act Density 0.014%

    No Known Activations