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

    Neuronpedia

    INDEX
    Explanations

    reading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     особи
    -0.07
    (force
    -0.07
     valore
    -0.07
    .compose
    -0.06
     Lean
    -0.06
     стратег
    -0.06
    gae
    -0.06
    .INTERNAL
    -0.06
    selection
    -0.06
    elm
    -0.06
    POSITIVE LOGITS
    υγ
    0.07
    buscar
    0.06
    Ross
    0.06
     Spice
    0.06
    ุด
    0.06
    族
    0.06
     رف
    0.06
    .term
    0.06
     작
    0.06
    ánh
    0.06
    Act Density 0.002%

    No Known Activations