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

    Neuronpedia

    INDEX
    Explanations

    prefixes of names and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     streetlight
    0.82
    որ
    0.81
    ethash
    0.80
    AL
    0.80
    स्‍
    0.79
    效
    0.79
    hlen
    0.77
    CNc
    0.77
    ASER
    0.76
    ेक्ट
    0.76
    POSITIVE LOGITS
     justo
    0.89
     plunged
    0.87
    ió
    0.84
     fêtes
    0.82
    ັງ
    0.82
    encio
    0.81
     يلي
    0.81
     ју
    0.81
     Yet
    0.80
     Anchor
    0.80
    Act Density 0.033%

    No Known Activations