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

    Neuronpedia

    INDEX
    Explanations

    mechanical computer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     be
    0.56
     of
    0.52
    ಕ್ತಿ
    0.51
    。
    0.49
     tacos
    0.49
     can
    0.49
    cing
    0.49
     Singapore
    0.46
     t
    0.46
    ?
    0.46
    POSITIVE LOGITS
     предыду
    0.49
    इल
    0.49
     έγινε
    0.49
     иногда
    0.48
     टमाटर
    0.48
    انب
    0.48
    県の
    0.47
    橿
    0.47
    Codes
    0.47
     робити
    0.47
    Act Density 0.000%

    No Known Activations