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

    Neuronpedia

    INDEX
    Explanations

    cannot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    зв
    -0.06
    experimental
    -0.06
    ить
    -0.06
     міжнарод
    -0.06
    ø
    -0.06
    mue
    -0.06
     превыш
    -0.06
    xFF
    -0.06
     Spar
    -0.06
    uf
    -0.06
    POSITIVE LOGITS
     schop
    0.07
    .RES
    0.07
     мали
    0.06
     tensors
    0.06
     veloc
    0.06
     경기도
    0.06
     trousers
    0.06
    からは
    0.06
    gens
    0.06
     contentious
    0.06
    Act Density 0.001%

    No Known Activations