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

    Neuronpedia

    INDEX
    Explanations

    explaining with a colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ².
    0.45
    ResourceId
    0.40
     εν
    0.39
    ˨
    0.38
    িও
    0.37
    </td>
    0.37
     In
    0.37
     Uda
    0.36
    SourceObject
    0.36
    ობას
    0.35
    POSITIVE LOGITS
    指出
    1.25
     explains
    1.18
    强调
    1.17
     mengatakan
    1.16
    強調
    1.15
     강조
    1.13
     explained
    1.13
     sottoline
    1.13
     explique
    1.12
     mention
    1.11
    Act Density 0.017%

    No Known Activations