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

    Neuronpedia

    INDEX
    Explanations

    naming or regulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    只会
    0.47
     поез
    0.45
    可以直接
    0.45
     문의
    0.45
    ointments
    0.44
    ‖</
    0.44
     उद्योगों
    0.43
    ército
    0.42
    Ships
    0.42
    だけに
    0.41
    POSITIVE LOGITS
    אל
    0.46
     hired
    0.45
     unin
    0.45
     sfondo
    0.45
     Nutt
    0.45
    jpeg
    0.45
    טא
    0.44
    太陽
    0.43
    א
    0.42
     ngu
    0.42
    Act Density 0.001%

    No Known Activations