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

    Neuronpedia

    INDEX
    Explanations

    calculating negative conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Auburn
    0.39
     ironically
    0.38
     liệt
    0.38
     entirely
    0.38
     drenched
    0.38
     Amherst
    0.38
    ట్ట
    0.37
    ವಾಗ
    0.37
     prison
    0.37
     replaced
    0.37
    POSITIVE LOGITS
    sud
    0.51
    Sud
    0.47
    Freeman
    0.46
    leistung
    0.45
    ˧
    0.45
    nahmen
    0.44
    perluan
    0.44
    average
    0.44
    linear
    0.43
     prescriptions
    0.43
    Act Density 0.001%

    No Known Activations