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

    Neuronpedia

    INDEX
    Explanations

    decreasing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     diversity
    -0.06
    Subset
    -0.06
     Two
    -0.06
     passing
    -0.06
    corev
    -0.06
     Сан
    -0.06
     Abb
    -0.06
    enha
    -0.06
    310
    -0.06
     diversos
    -0.06
    POSITIVE LOGITS
    .Extensions
    0.07
     lij
    0.06
     propel
    0.06
    輝
    0.06
    _BUILD
    0.06
    credible
    0.06
     #+#
    0.06
    �
    0.06
     Cuando
    0.06
    Conflict
    0.06
    Act Density 0.402%

    No Known Activations