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

    Neuronpedia

    INDEX
    Explanations

    lists of descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     availability
    0.47
     birdie
    0.45
     neither
    0.45
     luminos
    0.44
     adrenalin
    0.44
     investimento
    0.43
     runners
    0.43
     Onc
    0.43
     investment
    0.42
     assays
    0.42
    POSITIVE LOGITS
    í
    0.44
    💼
    0.43
    зки
    0.42
    ágico
    0.42
    zech
    0.42
    teki
    0.42
    erdas
    0.42
     ஆண்
    0.41
    abang
    0.41
    Transl
    0.41
    Act Density 0.005%

    No Known Activations