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

    Neuronpedia

    INDEX
    Explanations

    dense retrieval and vectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atthena
    0.47
    ский
    0.46
    ranial
    0.46
     домаћинствима
    0.46
     \\\
    0.43
     ಉತ್ತ
    0.42
     Masyarakat
    0.42
     पार
    0.42
    hehi
    0.41
    amatsu
    0.41
    POSITIVE LOGITS
    ب
    0.53
     liberate
    0.50
    ு
    0.50
     trei
    0.50
    B
    0.49
    ற்று
    0.49
     dois
    0.49
    According
    0.47
     vatten
    0.47
    Ur
    0.46
    Act Density 0.000%

    No Known Activations