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

    Neuronpedia

    INDEX
    Explanations

    rather

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sec
    -0.08
     Benson
    -0.07
    utdown
    -0.07
     Cisco
    -0.07
    deen
    -0.07
    763
    -0.07
    ディ
    -0.07
    На
    -0.07
     ПО
    -0.06
    on
    -0.06
    POSITIVE LOGITS
     rather
    0.15
    rather
    0.15
    Rather
    0.13
     Rather
    0.13
     render
    0.08
     ler
    0.08
     latter
    0.08
     khá
    0.08
    軽
    0.08
     wer
    0.07
    Act Density 0.015%

    No Known Activations