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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    努
    -0.07
    ofil
    -0.07
     campos
    -0.07
     Ödül
    -0.07
     darauf
    -0.07
    PointCloud
    -0.06
     팔
    -0.06
    なくな
    -0.06
    ROY
    -0.06
     overclock
    -0.06
    POSITIVE LOGITS
     '''
↵
    0.07
     prepend
    0.07
     json
    0.07
    [],↵
    0.06
    .J
    0.06
    .two
    0.06
    -з
    0.06
    cee
    0.06
    ประกอบ
    0.06
    ===
    0.06
    Act Density 0.003%

    No Known Activations