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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     miễn
    -0.07
    Enough
    -0.06
     Exped
    -0.06
    osterone
    -0.06
     类
    -0.06
    Travel
    -0.06
     $"{
    -0.06
    .Counter
    -0.06
     жит
    -0.06
    ourcing
    -0.06
    POSITIVE LOGITS
    φυ
    0.07
    の上
    0.07
    addTo
    0.07
     completeness
    0.07
    (padding
    0.07
    _social
    0.07
     seized
    0.07
    .Repository
    0.06
    (d
    0.06
    .E
    0.06
    Act Density 0.012%

    No Known Activations