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

    Neuronpedia

    INDEX
    Explanations

    each

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     зв
    -0.07
    动物
    -0.07
    иж
    -0.07
    _doc
    -0.07
     Dar
    -0.07
    یف
    -0.06
     Refuge
    -0.06
     IoT
    -0.06
     backpage
    -0.06
     Philosoph
    -0.06
    POSITIVE LOGITS
    ếu
    0.06
     سرد
    0.06
    /window
    0.06
    _ICON
    0.06
     тех
    0.06
     microscopic
    0.06
     SAF
    0.06
     ticks
    0.06
     Herbert
    0.06
    urgical
    0.06
    Act Density 0.001%

    No Known Activations