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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anki
    -0.09
    败
    -0.06
    erals
    -0.06
    าหาร
    -0.06
     ecs
    -0.06
    éli
    -0.06
     david
    -0.06
    boa
    -0.06
    ยาย
    -0.06
    ераль
    -0.06
    POSITIVE LOGITS
     presumably
    0.08
     JOIN
    0.07
     lived
    0.07
     perhaps
    0.07
    -not
    0.07
    uppercase
    0.07
     CreateUser
    0.07
     unmistak
    0.07
     neither
    0.07
     explicitly
    0.07
    Act Density 0.035%

    No Known Activations