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

    Neuronpedia

    INDEX
    Explanations

    vicuna

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    দান
    0.99
     menor
    0.90
     orang
    0.90
     expenditure
    0.87
     improvement
    0.86
     Typing
    0.86
    入り
    0.84
     resil
    0.84
     neurons
    0.81
     cerveau
    0.81
    POSITIVE LOGITS
    ius
    0.95
    xsi
    0.94
    𝒚
    0.91
    torn
    0.91
    у
    0.91
    Encryption
    0.87
    iu
    0.87
    𝒕
    0.87
    aaa
    0.87
     salient
    0.85
    Act Density 0.045%

    No Known Activations