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

    Neuronpedia

    INDEX
    Explanations

    file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.46
     nutric
    0.42
    tact
    0.40
     Lara
    0.40
    perd
    0.40
     ين
    0.38
     Poz
    0.38
     Heinrich
    0.38
     Ll
    0.37
    പ്പു
    0.37
    POSITIVE LOGITS
    finders
    0.48
    WAYS
    0.47
    finder
    0.45
    ওয়ে
    0.44
    ways
    0.43
     प्रदर्श
    0.43
    lengths
    0.43
    рование
    0.43
    WAY
    0.43
    ingale
    0.43
    Act Density 0.012%

    No Known Activations