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

    Neuronpedia

    INDEX
    Explanations

    code/technical data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    捡
    -0.07
    NESS
    -0.07
     ≤
    -0.06
     little
    -0.06
    励志
    -0.06
    大小
    -0.06
    alis
    -0.06
    行李
    -0.06
    hammad
    -0.06
    ám
    -0.06
    POSITIVE LOGITS
    _imgs
    0.07
     lugar
    0.07
    ARIO
    0.07
     frag
    0.07
    生产
    0.07
    ATING
    0.07
    asts
    0.07
     graphics
    0.07
    comput
    0.07
     membr
    0.07
    Act Density 0.017%

    No Known Activations