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

    Neuronpedia

    INDEX
    Explanations

    then/to followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    м
    0.80
     questo
    0.68
     mío
    0.66
     biosynthetic
    0.63
     există
    0.63
     încep
    0.63
    ﺏ
    0.63
     turmoil
    0.62
     cheio
    0.61
    م
    0.60
    POSITIVE LOGITS
    ina
    0.61
     Marine
    0.61
    ‍♀️
    0.61
    linson
    0.60
    ार्‍या
    0.59
    אנ
    0.58
     {#
    0.56
     而且
    0.56
    Marine
    0.55
    มีการ
    0.55
    Act Density 3.926%

    No Known Activations