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

    Neuronpedia

    INDEX
    Explanations

    dig

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     поможет
    -0.07
    liness
    -0.07
     smlouvy
    -0.06
     помогает
    -0.06
    -lang
    -0.06
    cw
    -0.06
     muz
    -0.06
     consumes
    -0.06
     кількості
    -0.06
     sz
    -0.06
    POSITIVE LOGITS
     enemy
    0.07
    Instagram
    0.07
     despite
    0.06
     assumed
    0.06
    Dan
    0.06
     successfully
    0.06
     respawn
    0.06
     ولي
    0.06
     Stops
    0.06
    getAttribute
    0.06
    Act Density 0.000%

    No Known Activations