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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    τερη
    -0.07
    obia
    -0.07
    ่างก
    -0.07
    atoria
    -0.07
    ním
    -0.07
    Wik
    -0.07
    �에
    -0.06
     하는
    -0.06
    anyak
    -0.06
     kako
    -0.06
    POSITIVE LOGITS
     Mountain
    0.07
    .Claims
    0.07
    )((
    0.06
    训
    0.06
     chew
    0.06
    rv
    0.06
     scalp
    0.06
     Bates
    0.06
    :checked
    0.06
     сал
    0.06
    Act Density 0.010%

    No Known Activations