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

    Neuronpedia

    INDEX
    Explanations

    processes or stages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    टिक
    0.63
    Breakpoint
    0.57
    ऊंगा
    0.56
    ০০
    0.55
    ப்படுத்த
    0.54
     twentieth
    0.54
    Estado
    0.54
     secreted
    0.54
    っしゃ
    0.54
    ぁ
    0.54
    POSITIVE LOGITS
     with
    0.73
     sırasında
    0.72
     effettu
    0.62
    过程中
    0.62
    完毕
    0.62
     işlemi
    0.61
    with
    0.61
    後の
    0.60
    কারী
    0.59
     과정
    0.59
    Act Density 2.335%

    No Known Activations