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

    Neuronpedia

    INDEX
    Explanations

    examples with instructions, lists, or formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mediation
    0.43
     diffused
    0.42
     difusión
    0.42
     centralization
    0.42
     histological
    0.40
     extremities
    0.39
     roundabout
    0.39
     hysterical
    0.39
     messes
    0.39
     pomaga
    0.38
    POSITIVE LOGITS
    critic
    0.50
    reasonably
    0.49
     कार्यकारी
    0.49
     Paid
    0.48
    assertions
    0.47
    APPE
    0.45
    sprach
    0.44
    نك
    0.44
    maar
    0.43
    BUGFS
    0.43
    Act Density 0.003%

    No Known Activations