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

    Neuronpedia

    INDEX
    Explanations

    player rotation and substitution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arrogant
    0.41
     ước
    0.39
    擷
    0.38
     rejection
    0.36
     préd
    0.36
     glic
    0.36
     процессы
    0.36
     കമ്പ
    0.35
     방법을
    0.35
    triangleq
    0.35
    POSITIVE LOGITS
     substitutions
    1.11
     rotates
    1.05
     rotation
    1.02
     rotations
    1.02
     bench
    0.98
     rotate
    0.98
     lineup
    0.98
     substitution
    0.98
     substitutes
    0.96
     rotating
    0.94
    Act Density 0.006%

    No Known Activations