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

    Neuronpedia

    INDEX
    Explanations

    off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     bred
    -0.07
     superst
    -0.07
     Common
    -0.07
     wears
    -0.07
     haz
    -0.07
    common
    -0.07
     kiếm
    -0.06
     accommodate
    -0.06
     reputable
    -0.06
    POSITIVE LOGITS
    -employed
    0.07
     تلفن
    0.07
     conex
    0.07
    461
    0.07
     информ
    0.07
     çünkü
    0.07
     generate
    0.06
     networking
    0.06
    ////////////
    0.06
    .erb
    0.06
    Act Density 0.009%

    No Known Activations