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

    Neuronpedia

    INDEX
    Explanations

    This

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ఎం
    0.45
     повин
    0.45
     повинні
    0.40
     ਟ
    0.39
     गुना
    0.38
     reflexes
    0.38
     හැකි
    0.38
     грн
    0.38
    الو
    0.37
    ならでは
    0.37
    POSITIVE LOGITS
     This
    0.95
    this
    0.93
    これは
    0.93
     this
    0.92
    This
    0.89
     هذا
    0.84
     это
    0.82
     THIS
    0.82
     これは
    0.80
     questo
    0.79
    Act Density 0.207%

    No Known Activations