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

    Neuronpedia

    INDEX
    Explanations

    new object declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    서
    0.73
    あまり
    0.73
     outcrops
    0.68
    ይታ
    0.66
    しい
    0.64
    െ
    0.64
    ियत
    0.64
    ৫
    0.63
    美元
    0.63
    िया
    0.62
    POSITIVE LOGITS
    ו
    0.81
    েও
    0.72
    ्च
    0.66
    ে
    0.65
    IST
    0.64
    ात
    0.64
    ा
    0.62
    THING
    0.61
     וע
    0.61
    aft
    0.59
    Act Density 0.164%

    No Known Activations