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

    Neuronpedia

    INDEX
    Explanations

    identifying failure causes and specific contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    തെ
    0.42
     olyan
    0.40
     cuyas
    0.38
     bestimmte
    0.38
     เหมือน
    0.37
     empêcher
    0.37
     পড়
    0.36
    看似
    0.36
    йга
    0.36
    の変化
    0.36
    POSITIVE LOGITS
     embrace
    0.47
     checkFor
    0.46
     embraces
    0.44
     rampant
    0.43
     embracing
    0.40
     Embrace
    0.39
    自带
    0.39
     właśnie
    0.39
     practising
    0.38
    checkFor
    0.38
    Act Density 0.045%

    No Known Activations