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

    Neuronpedia

    INDEX
    Explanations

    stuck in analysis paralysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    εν
    0.50
     primeiras
    0.50
     buen
    0.47
     diagrams
    0.47
     કો
    0.46
     pc
    0.45
     पनि
    0.45
     brows
    0.45
    ढे
    0.44
    तियों
    0.44
    POSITIVE LOGITS
    有一些
    0.46
     अशी
    0.44
     Leid
    0.41
     Brandenburg
    0.41
    有一种
    0.41
    ropolitan
    0.40
    trusive
    0.40
    有一个
    0.39
    ••
    0.39
     Impulse
    0.39
    Act Density 0.006%

    No Known Activations