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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Adapter
    -0.07
     faut
    -0.07
     atleast
    -0.06
     Schw
    -0.06
     леч
    -0.06
    แค
    -0.06
     admittedly
    -0.06
    Launcher
    -0.06
     jaký
    -0.06
    expression
    -0.06
    POSITIVE LOGITS
    Segment
    0.08
     thinking
    0.07
     مقدم
    0.07
    -transparent
    0.07
    فصل
    0.07
     modulus
    0.06
    οκ
    0.06
    Decision
    0.06
    剧
    0.06
    칭
    0.06
    Act Density 0.009%

    No Known Activations