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

    Neuronpedia

    INDEX
    Explanations

    Apologies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eware
    -0.06
    sup
    -0.06
     Их
    -0.06
     زر
    -0.06
     followers
    -0.06
     никто
    -0.06
    -normal
    -0.06
    _wrapper
    -0.06
    níky
    -0.06
     musí
    -0.06
    POSITIVE LOGITS
    opp
    0.07
     signifies
    0.06
     relocated
    0.06
    belum
    0.06
     existed
    0.06
    取消
    0.06
    usunda
    0.06
     cooperation
    0.06
    oppel
    0.06
    USTOM
    0.06
    Act Density 0.011%

    No Known Activations