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

    Neuronpedia

    INDEX
    Explanations

    studies over a period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _UnityEngine
    -0.07
    税
    -0.07
    dp
    -0.07
     obj
    -0.07
     Jessie
    -0.07
     Taking
    -0.07
    انی
    -0.06
    210
    -0.06
    CUDA
    -0.06
    级
    -0.06
    POSITIVE LOGITS
    assoc
    0.06
    >');↵
    0.06
    ifle
    0.06
     unconditional
    0.06
     محافظ
    0.06
       ↵    ↵
    0.06
    :void
    0.05
     Suff
    0.05
    وح
    0.05
    exao
    0.05
    Act Density 0.014%

    No Known Activations