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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     datap
    -0.07
    20
    -0.07
    zp
    -0.07
     spd
    -0.06
    -haired
    -0.06
    ่ะ
    -0.06
    15
    -0.06
     repaired
    -0.06
    28
    -0.06
    orpor
    -0.06
    POSITIVE LOGITS
     One
    0.11
    (one
    0.11
    .One
    0.09
    one
    0.09
    .ONE
    0.09
    One
    0.09
    _one
    0.09
     ONE
    0.09
    ONE
    0.08
     one
    0.07
    Act Density 0.013%

    No Known Activations