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

    Neuronpedia

    INDEX
    Explanations

    Code/technical issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CHUNK
    -0.07
     wil
    -0.06
    中央
    -0.06
    那样
    -0.06
    .Include
    -0.06
    -0.06
    >Your
    -0.06
    “No
    -0.06
    .Identity
    -0.06
    his
    -0.06
    POSITIVE LOGITS
    _tr
    0.06
    roc
    0.06
    _polygon
    0.06
     dx
    0.06
     scares
    0.06
    .hamcrest
    0.06
     Eu
    0.06
    Ale
    0.06
     ms
    0.06
     vue
    0.06
    Act Density 0.000%

    No Known Activations