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

    Neuronpedia

    INDEX
    Explanations

    different types of text introductions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ské
    0.58
    ating
    0.55
    ening
    0.53
    ushing
    0.52
    án
    0.52
    msup
    0.52
     तिथि
    0.51
    ОВ
    0.51
    ologies
    0.50
    ни
    0.50
    POSITIVE LOGITS
    a
    0.84
    ه
    0.77
    aaf
    0.66
    ה
    0.66
    ت
    0.64
    മ
    0.64
    aib
    0.61
    𝘁
    0.61
     garrison
    0.61
    aing
    0.61
    Act Density 0.023%

    No Known Activations