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

    Neuronpedia

    INDEX
    Explanations

    foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Courtesy
    -0.07
    Suit
    -0.07
     Strikes
    -0.07
     specifying
    -0.07
     BorderLayout
    -0.07
     became
    -0.07
     ft
    -0.07
     ומת
    -0.07
    Posts
    -0.07
     Jonathan
    -0.07
    POSITIVE LOGITS
    ô
    0.06
           ↵
    0.06
     תמיד
    0.06
    滾
    0.06
    葵
    0.06
    ADER
    0.06
     Rou
    0.06
     Rod
    0.06
     IK
    0.06
     kvin
    0.06
    Act Density 0.120%

    No Known Activations