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

    Neuronpedia

    INDEX
    Explanations

    sky

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "For
    -0.07
    -language
    -0.07
     punishing
    -0.07
    _female
    -0.07
     陳
    -0.07
     displacement
    -0.07
     Johann
    -0.06
    “For
    -0.06
    Fetching
    -0.06
     Ged
    -0.06
    POSITIVE LOGITS
     Sky
    0.11
     sky
    0.09
     skies
    0.09
    Sky
    0.08
     天
    0.07
    .stdin
    0.06
    sunuz
    0.06
    HY
    0.06
     helmets
    0.06
     معل
    0.06
    Act Density 0.012%

    No Known Activations