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

    Neuronpedia

    INDEX
    Explanations

    198

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NIL
    -0.08
    και
    -0.06
    우스
    -0.06
     biscuits
    -0.06
     ديسمبر
    -0.06
    ると
    -0.06
     Rouge
    -0.06
    uD
    -0.06
    ammo
    -0.06
     경기도
    -0.06
    POSITIVE LOGITS
     conferred
    0.07
     underline
    0.06
    еної
    0.06
     Cameron
    0.06
     minlength
    0.06
    (reader
    0.06
    (base
    0.06
     wang
    0.06
     RESOURCE
    0.06
     erót
    0.06
    Act Density 0.015%

    No Known Activations