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

    Neuronpedia

    INDEX
    Explanations

    Punctuation and "and"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الاج
    -0.07
     softmax
    -0.06
    出口
    -0.06
     Parkway
    -0.06
     blunt
    -0.06
     "")
    -0.06
    �
    -0.06
    Kin
    -0.06
     discarded
    -0.06
     حمل
    -0.06
    POSITIVE LOGITS
     Pierre
    0.06
    >';
    0.06
    Overlay
    0.06
    λευτα
    0.06
     Day
    0.06
     اگر
    0.06
    DAY
    0.06
    hle
    0.06
    anteed
    0.06
    ีผ
    0.06
    Act Density 0.022%

    No Known Activations