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

    Neuronpedia

    INDEX
    Explanations

    Assistant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chu
    -0.07
    (variable
    -0.07
     antigen
    -0.07
     anus
    -0.06
    comboBox
    -0.06
     Astroph
    -0.06
    IconModule
    -0.06
    -invalid
    -0.06
    ,x
    -0.06
    電
    -0.06
    POSITIVE LOGITS
     inspires
    0.08
     ASSIGN
    0.07
     strpos
    0.06
    RYPT
    0.06
    ύπ
    0.06
    ullo
    0.06
     remotely
    0.06
    Assistant
    0.06
     lifelong
    0.06
    žila
    0.06
    Act Density 0.004%

    No Known Activations