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

    Neuronpedia

    INDEX
    Explanations

    institutional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (IP
    -0.07
     HEAD
    -0.07
    ۶
    -0.07
     حوزه
    -0.06
    ۸
    -0.06
    lena
    -0.06
    <void
    -0.06
    763
    -0.06
     Accuracy
    -0.06
    egers
    -0.06
    POSITIVE LOGITS
     institutional
    0.13
     Institutional
    0.11
    Intl
    0.07
    ilece
    0.07
    .addClass
    0.06
     CCP
    0.06
     канди
    0.06
    .EventSystems
    0.06
    尿
    0.06
     disgu
    0.06
    Act Density 0.001%

    No Known Activations