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

    Neuronpedia

    INDEX
    Explanations

    nodes in a cluster

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    לי
    0.52
     envis
    0.50
     tener
    0.46
     have
    0.46
     Enzyme
    0.44
     February
    0.44
     Substitution
    0.43
     Unit
    0.43
     Parameters
    0.43
    ണ്ണ
    0.42
    POSITIVE LOGITS
    categorias
    0.56
    довле
    0.54
    гает
    0.52
    chairs
    0.52
     ताब
    0.51
    t
    0.50
    emonic
    0.49
    ುದು
    0.49
    scaping
    0.48
    quellen
    0.47
    Act Density 0.000%

    No Known Activations