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

    Neuronpedia

    INDEX
    Explanations

    ::

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    菟
    -0.08
    ✎
    -0.07
    펫
    -0.07
     Education
    -0.07
    玳
    -0.07
    .nii
    -0.07
    啐
    -0.07
     дер
    -0.07
    �
    -0.07
     stumbling
    -0.07
    POSITIVE LOGITS
    ():↵
    0.08
    	lua
    0.08
    ():
↵
    0.07
    (Symbol
    0.07
     הישרא
    0.07
    (instruction
    0.07
     práctica
    0.07
    '}↵
    0.07
     компания
    0.07
    _constraint
    0.07
    Act Density 0.002%

    No Known Activations