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

    Neuronpedia

    INDEX
    Explanations

    # or *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Written
    -0.08
    (Register
    -0.07
     Wrestling
    -0.07
     Benny
    -0.07
    破碎
    -0.06
     Bud
    -0.06
     �
    -0.06
     Crusher
    -0.06
    褫
    -0.06
    申
    -0.06
    POSITIVE LOGITS
     five
    0.07
    וכה
    0.07
     unforgettable
    0.07
    あの
    0.07
    お�
    0.07
     đua
    0.06
    els
    0.06
     العلاقات
    0.06
     trainable
    0.06
     alphabetical
    0.06
    Act Density 0.001%

    No Known Activations