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

    Neuronpedia

    INDEX
    Explanations

    naive approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    洗濯
    0.42
    परी
    0.42
     Gespräch
    0.42
    хий
    0.41
     beard
    0.41
    jera
    0.41
    StoredKeys
    0.41
     revolt
    0.40
    неш
    0.40
    ALTERNATIVE
    0.40
    POSITIVE LOGITS
    tyw
    0.50
     surrounded
    0.49
    past
    0.45
     spong
    0.45
     located
    0.41
     kan
    0.41
     teng
    0.41
     bounded
    0.40
     सकता
    0.40
     Teng
    0.40
    Act Density 0.002%

    No Known Activations