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

    Neuronpedia

    INDEX
    Explanations

    above or below

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    쭤
    0.65
     लीजिएगा
    0.64
     speziell
    0.64
    ournal
    0.64
    lysninger
    0.63
     पूछते
    0.63
    ให้กับ
    0.61
    കാന്‍
    0.61
     सुनते
    0.61
    ዎታል
    0.61
    POSITIVE LOGITS
     above
    5.87
     below
    5.36
    above
    5.23
    below
    4.89
     Above
    4.88
    Above
    4.79
     Below
    4.60
    Below
    4.48
     acima
    4.48
     ABOVE
    4.29
    Act Density 0.458%

    No Known Activations