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

    Neuronpedia

    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Анг
    -0.06
    문
    -0.06
     instructors
    -0.06
     Yup
    -0.06
    ]);
↵
↵
    -0.06
     Νο
    -0.06
     helicopter
    -0.06
    Chapter
    -0.06
     _|
    -0.06
     Pension
    -0.06
    POSITIVE LOGITS
    Від
    0.08
    uji
    0.07
     DEAD
    0.07
     teknoloj
    0.06
     Musik
    0.06
    على
    0.06
    213
    0.06
    crease
    0.06
    ोज
    0.06
     Від
    0.06
    Act Density 0.000%

    No Known Activations