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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Blood
    -0.07
     Globe
    -0.07
    -blood
    -0.06
    indy
    -0.06
     мере
    -0.06
    стро
    -0.06
    Any
    -0.06
    iversary
    -0.06
    urma
    -0.06
    Maximum
    -0.06
    POSITIVE LOGITS
     pulver
    0.07
     ply
    0.07
     تکن
    0.06
     syst
    0.06
     jogo
    0.06
    роф
    0.06
    632
    0.06
     compra
    0.06
     expressive
    0.06
    079
    0.06
    Act Density 0.014%

    No Known Activations