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

    Neuronpedia

    INDEX
    Explanations

    gradable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _lastname
    -0.06
    لوب
    -0.06
    _CNTL
    -0.06
    \Bridge
    -0.06
    卢
    -0.06
    重要
    -0.06
     صاد
    -0.06
     elapsed
    -0.06
    法
    -0.06
     爱
    -0.06
    POSITIVE LOGITS
    gradable
    0.12
     Gig
    0.07
     DAG
    0.06
     missionaries
    0.06
    abase
    0.06
     Sask
    0.06
     retrospect
    0.06
    465
    0.06
    ihar
    0.06
    .LOC
    0.06
    Act Density 0.001%

    No Known Activations