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

    Neuronpedia

    INDEX
    Explanations

    non-English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.77
    0.68
    t
    0.62
    st
    0.58
    c
    0.58
     I
    0.56
    er
    0.55
    a
    0.52
    5
    0.52
     to
    0.51
    POSITIVE LOGITS
    0.56
    validacion
    0.55
     ойной
    0.54
     ආහාර
    0.53
    餞
    0.52
    hkse
    0.52
     රස
    0.52
     Paryayvachi
    0.51
    resTmp
    0.51
     конференции
    0.51
    Act Density 0.001%

    No Known Activations