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

    Neuronpedia

    INDEX
    Explanations

    internet and tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rm
    0.48
     examiners
    0.48
     photom
    0.47
    ampang
    0.45
     под
    0.45
     raids
    0.45
    ゲ
    0.44
     amplitudes
    0.44
     quedar
    0.43
    л
    0.43
    POSITIVE LOGITS
    ऊदी
    0.49
    Hot
    0.44
     Расійскай
    0.44
     Cognitive
    0.44
    Wells
    0.43
    aneswar
    0.43
     Metabolism
    0.43
    要有
    0.42
    و
    0.42
    Variable
    0.41
    Act Density 0.001%

    No Known Activations