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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     совершенно
    -0.07
     Beard
    -0.07
    шла
    -0.06
     сдел
    -0.06
     tour
    -0.06
     Helvetica
    -0.06
     Hed
    -0.06
    ít
    -0.06
     повинен
    -0.06
    гл
    -0.06
    POSITIVE LOGITS
    IntPtr
    0.07
    ?>
↵
    0.07
    -create
    0.06
    ,$_
    0.06
    .Generic
    0.06
    _online
    0.06
     transported
    0.06
     ]
↵
    0.06
     відповід
    0.06
     ek
    0.06
    Act Density 0.031%

    No Known Activations