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

    Neuronpedia

    INDEX
    Explanations

    ices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    直到
    -0.07
    ゝ
    -0.07
    _ONLY
    -0.07
     misled
    -0.06
    FLAGS
    -0.06
     promise
    -0.06
    joined
    -0.06
    מלח
    -0.06
    长时间
    -0.06
    bower
    -0.06
    POSITIVE LOGITS
    ICS
    0.07
     alan
    0.07
     glance
    0.07
    ="{
    0.07
    区域性
    0.07
    逛
    0.06
     gamers
    0.06
    鳓
    0.06
     Basin
    0.06
    mary
    0.06
    Act Density 0.005%

    No Known Activations