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

    Neuronpedia

    INDEX
    Explanations

    ):

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Liz
    -0.07
     utiliza
    -0.07
     authentic
    -0.06
     rol
    -0.06
    ��
    -0.06
    рол
    -0.06
    Nice
    -0.06
     VERSION
    -0.06
    antity
    -0.06
     rustic
    -0.06
    POSITIVE LOGITS
    509
    0.07
    /utility
    0.06
    inging
    0.06
    Datos
    0.06
     prisoners
    0.06
    ());
↵
    0.06
     ){↵↵
    0.06
    anych
    0.06
     SUM
    0.06
    ometer
    0.06
    Act Density 0.028%

    No Known Activations