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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Includes
    -0.07
     cancelling
    -0.06
     Byrne
    -0.06
    hton
    -0.06
     такая
    -0.06
    機
    -0.06
     Каз
    -0.06
     newfound
    -0.06
     Produce
    -0.06
     Moy
    -0.06
    POSITIVE LOGITS
    _change
    0.06
    μει
    0.06
    gets
    0.06
    िण
    0.06
     pán
    0.06
     ],↵↵
    0.06
    작
    0.06
    ième
    0.06
     Sah
    0.06
    zed
    0.06
    Act Density 0.061%

    No Known Activations