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

    Neuronpedia

    INDEX
    Explanations

    initial evaluations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ERISA
    0.44
     transaction
    0.44
    يان
    0.42
     iniciativa
    0.42
     ủng
    0.41
     unrelated
    0.40
    erai
    0.40
     reorganization
    0.40
     documentation
    0.40
     eldest
    0.40
    POSITIVE LOGITS
    Squ
    0.47
    *
    0.46
     φύ
    0.46
    Substitute
    0.46
    Distribution
    0.45
    Contract
    0.45
    ಖ
    0.44
    по
    0.44
    Lev
    0.44
     சதவீ
    0.44
    Act Density 0.004%

    No Known Activations