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

    Neuronpedia

    INDEX
    Explanations

    high cheekbones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᅵ
    0.48
     मिनिस्टर
    0.48
    ICIENCY
    0.47
    批評
    0.46
     unwillingness
    0.46
     Aziz
    0.45
     обязанности
    0.45
    🔢
    0.45
    🤱
    0.45
     disagreements
    0.44
    POSITIVE LOGITS
     and
    0.65
     frame
    0.58
     sturdy
    0.57
     flared
    0.56
     fitted
    0.55
     hydraulic
    0.55
     tapered
    0.55
     resin
    0.54
     with
    0.54
     wood
    0.54
    Act Density 0.019%

    No Known Activations