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

    Neuronpedia

    INDEX
    Explanations

    place names, people, brands, specific objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    immutable
    0.47
     massless
    0.43
    ни
    0.42
    כה
    0.41
    били
    0.41
    codigo
    0.40
    containers
    0.39
    ígeno
    0.39
     मनाया
    0.38
    invalidate
    0.38
    POSITIVE LOGITS
    :.
    0.51
     alertDialog
    0.48
     Improvements
    0.47
     types
    0.46
     standart
    0.46
     with
    0.46
     improvement
    0.46
     varies
    0.46
     From
    0.45
     With
    0.45
    Act Density 0.001%

    No Known Activations