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

    Neuronpedia

    INDEX
    Explanations

    supporting developer updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    每年
    0.44
    :~
    0.43
    ㄻ
    0.41
     razvoja
    0.40
    rapa
    0.40
     exports
    0.38
    Spa
    0.38
     vaksin
    0.38
    rijving
    0.38
    RootManager
    0.38
    POSITIVE LOGITS
     Batik
    0.43
     теория
    0.43
     механизм
    0.42
    oteca
    0.41
    ain
    0.41
     मात
    0.41
    il
    0.40
     оско
    0.40
     Isis
    0.40
    രിക്കുന്നു
    0.39
    Act Density 0.001%

    No Known Activations