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

    Neuronpedia

    INDEX
    Explanations

    disclosure, learning, encourage, synapse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?
    0.50
     bhavanti
    0.46
    тих
    0.45
    許可
    0.42
    ))
    0.42
    一样的
    0.42
    表情
    0.41
    仯
    0.40
    <0xA4>
    0.39
    ComponentModel
    0.39
    POSITIVE LOGITS
     therefore
    0.52
    四年
    0.46
    curities
    0.46
    putText
    0.45
     fetish
    0.44
    voer
    0.44
     scents
    0.43
     poiché
    0.43
    oría
    0.43
     လ
    0.42
    Act Density 0.000%

    No Known Activations