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

    Neuronpedia

    INDEX
    Explanations

    tell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CAP
    -0.08
    Time
    -0.07
    建
    -0.07
     fich
    -0.07
    Weak
    -0.06
    Lv
    -0.06
    .uml
    -0.06
     Morse
    -0.06
    ctest
    -0.06
    _marks
    -0.06
    POSITIVE LOGITS
    	HashMap
    0.07
    setSize
    0.06
    ETERS
    0.06
     та
    0.06
    олод
    0.06
    Frameworks
    0.06
     الت
    0.06
     وظ
    0.06
     atheists
    0.06
     материалов
    0.06
    Act Density 0.273%

    No Known Activations