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

    Neuronpedia

    INDEX
    Explanations

    these

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     solitude
    -0.07
    are
    -0.07
    "is
    -0.06
    _get
    -0.06
    (prog
    -0.06
    _material
    -0.06
    查询
    -0.06
    (flag
    -0.06
     cou
    -0.06
     battery
    -0.06
    POSITIVE LOGITS
    idine
    0.06
    ὐ
    0.06
     neod
    0.06
     α
    0.06
    θος
    0.06
     Η
    0.06
    的に
    0.06
    حيح
    0.06
    丝
    0.06
    Adam
    0.06
    Act Density 0.019%

    No Known Activations