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

    Neuronpedia

    INDEX
    Explanations

    after

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .lastname
    -0.07
    enco
    -0.06
     імені
    -0.06
     liners
    -0.06
    >In
    -0.06
     Glad
    -0.06
    าศาสตร
    -0.06
     boutique
    -0.06
     ฮ
    -0.06
     letto
    -0.06
    POSITIVE LOGITS
    After
    0.07
    ミ
    0.06
    στε
    0.06
     اص
    0.06
    Penn
    0.06
     après
    0.06
     ödül
    0.06
     After
    0.06
    для
    0.06
     Kim
    0.06
    Act Density 0.020%

    No Known Activations