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

    Neuronpedia

    INDEX
    Explanations

    dis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Source
    -0.07
     spying
    -0.06
    gorithms
    -0.06
    ech
    -0.06
     reactor
    -0.06
    ixedReality
    -0.06
    aves
    -0.06
    (rule
    -0.06
     لر
    -0.06
     these
    -0.06
    POSITIVE LOGITS
    UPI
    0.07
     プ
    0.07
    Poly
    0.06
     نی
    0.06
    _length
    0.06
    Attempting
    0.06
    postgresql
    0.06
    ヒ
    0.06
    .getenv
    0.06
     ').
    0.06
    Act Density 0.159%

    No Known Activations