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

    Neuronpedia

    INDEX
    Explanations

    criticisms in news

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    เหมาะ
    -0.07
    โรงแรม
    -0.07
    ملة
    -0.06
     rifles
    -0.06
    Οι
    -0.06
    άς
    -0.06
    (device
    -0.06
    _Column
    -0.06
     decrease
    -0.06
    legal
    -0.06
    POSITIVE LOGITS
     missile
    0.07
     تلویزیون
    0.06
     Ди
    0.06
     flav
    0.06
    /Framework
    0.06
     Missile
    0.06
    Container
    0.06
    <f
    0.06
     natuur
    0.06
     OnCollision
    0.06
    Act Density 0.004%

    No Known Activations