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

    Neuronpedia

    INDEX
    Explanations

    dark themes or humor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     xia
    0.45
    eness
    0.43
     tiled
    0.42
     tower
    0.41
     Hamiltonian
    0.41
    rophication
    0.41
    aj
    0.41
    owness
    0.41
     described
    0.41
     restored
    0.40
    POSITIVE LOGITS
     registros
    0.46
    ELEASE
    0.41
    ۴
    0.41
    まずは
    0.40
    TotalPrice
    0.40
    IP
    0.40
    BUT
    0.40
    Deliver
    0.39
    ंसू
    0.39
    లోనే
    0.38
    Act Density 0.009%

    No Known Activations