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

    Neuronpedia

    INDEX
    Explanations

    X followed by Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ERC
    0.38
     Utah
    0.38
    ພວກ
    0.38
    ourt
    0.37
     ATV
    0.36
    encore
    0.36
    icles
    0.36
    certs
    0.36
    nearby
    0.36
    abul
    0.35
    POSITIVE LOGITS
     Flatten
    0.43
     flatten
    0.42
    flatten
    0.40
     ライン
    0.39
    льній
    0.39
     línea
    0.38
    Flatten
    0.38
    Apply
    0.37
     vân
    0.37
    माना
    0.36
    Act Density 0.001%

    No Known Activations