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

    Neuronpedia

    INDEX
    Explanations

    spanish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CD
    -0.08
    Ord
    -0.07
     ld
    -0.07
    _MD
    -0.07
     Lin
    -0.07
    :boolean
    -0.06
     Ferdinand
    -0.06
     Jiang
    -0.06
     DD
    -0.06
     Elizabeth
    -0.06
    POSITIVE LOGITS
     aqu
    0.10
    Aqu
    0.09
     Aqu
    0.08
     aquel
    0.08
    894
    0.07
     oak
    0.07
     بح
    0.06
    448
    0.06
    قی
    0.06
    �
    0.06
    Act Density 0.005%

    No Known Activations