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

    Neuronpedia

    INDEX
    Explanations

    hyphenated word components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ِمض
    1.02
     !_
    0.92
     (_,
    0.85
     _,
    0.84
    ሶች
    0.83
    َح
    0.81
     _______
    0.80
    क़्त
    0.80
     теркәлүсез
    0.79
    ূর্ন
    0.78
    POSITIVE LOGITS
    -
    4.89
    -(
    2.78
    -[
    2.71
    -*
    2.68
    -...
    2.66
    ـ
    2.66
    -<
    2.64
    -'
    2.60
    -{
    2.57
    -$
    2.56
    Act Density 1.922%

    No Known Activations