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

    Neuronpedia

    INDEX
    Explanations

    e

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wir
    -0.07
     eighteen
    -0.06
    606
    -0.06
    	bit
    -0.06
     �
    -0.06
    609
    -0.06
     кус
    -0.06
    01
    -0.06
    hyp
    -0.06
     цю
    -0.06
    POSITIVE LOGITS
    owering
    0.07
    productive
    0.07
    anded
    0.07
    iva
    0.07
     Viking
    0.07
     dziewcz
    0.07
     accountable
    0.07
    多い
    0.06
    Neal
    0.06
    :)↵
    0.06
    Act Density 0.013%

    No Known Activations