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

    Neuronpedia

    INDEX
    Explanations

    predictive analytics allows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    セレ
    0.41
     breach
    0.40
    0.37
    ᱹ
    0.36
    uerre
    0.36
     soit
    0.35
     विगत
    0.35
    rás
    0.35
     ф
    0.35
     कमे
    0.35
    POSITIVE LOGITS
    Allow
    0.41
     हिर
    0.40
     majeur
    0.40
     السادس
    0.39
     позволяют
    0.39
     उठ
    0.38
     chamado
    0.38
    స్తున్నారు
    0.38
     സമ്
    0.38
     NodeType
    0.37
    Act Density 0.001%

    No Known Activations