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

    Neuronpedia

    INDEX
    Explanations

    alphabetical lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lorsque
    0.45
     khiến
    0.40
     ठीक
    0.40
     із
    0.40
    sqcup
    0.39
    <unused527>
    0.38
     řek
    0.38
     sehingga
    0.38
    śli
    0.38
    șit
    0.38
    POSITIVE LOGITS
    African
    0.52
    Agricultural
    0.52
    BagConstraints
    0.49
    Angle
    0.48
    Audio
    0.47
     Adams
    0.47
    Ant
    0.47
    Animal
    0.47
    Argentina
    0.46
     あ
    0.46
    Act Density 0.026%

    No Known Activations