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

    Neuronpedia

    INDEX
    Explanations

    nostalgia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    1.58
    נ
    1.38
    를
    1.34
    e
    1.25
    y
    1.24
    কে
    1.21
    తో
    1.17
    ا
    1.16
    లో
    1.15
     ocen
    1.15
    POSITIVE LOGITS
    st
    1.63
    ारा
    1.03
    тном
    0.98
    kho
    0.96
    log
    0.96
    stion
    0.95
    stest
    0.95
    ない
    0.94
    ल
    0.94
    simile
    0.93
    Act Density 0.001%

    No Known Activations