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

    Neuronpedia

    INDEX
    Explanations

    trend

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anyways
    -0.07
     chắc
    -0.07
    鲦
    -0.07
    �
    -0.07
    观影
    -0.07
    acias
    -0.06
     Candidate
    -0.06
    竟是
    -0.06
    持ってい
    -0.06
    Saving
    -0.06
    POSITIVE LOGITS
    ﻚ
    0.07
    ipse
    0.07
     cuff
    0.06
     qualifiers
    0.06
    퀠
    0.06
    مقاطع
    0.06
    工业企业
    0.06
     blat
    0.06
    _quotes
    0.06
    checks
    0.06
    Act Density 0.024%

    No Known Activations