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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slogan
    -0.07
    kontakte
    -0.07
    	Vector
    -0.06
     token
    -0.06
    .sd
    -0.06
     خدم
    -0.06
     удар
    -0.06
     leadership
    -0.06
    "After
    -0.06
    .No
    -0.06
    POSITIVE LOGITS
     En
    0.07
    ینگ
    0.06
    En
    0.06
    除了
    0.06
    ὲ
    0.06
    ۴
    0.06
     ΠΑΝ
    0.06
     en
    0.06
     červ
    0.06
    POSE
    0.06
    Act Density 0.012%

    No Known Activations