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

    Neuronpedia

    INDEX
    Explanations

    genres and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     norm
    0.36
    ጺ
    0.35
     operation
    0.35
     উপমহাদেশ
    0.34
     faith
    0.34
     need
    0.34
     theme
    0.34
     chunk
    0.34
    Defer
    0.34
     answer
    0.33
    POSITIVE LOGITS
     আগামী
    0.39
     pop
    0.39
    णाऱ्या
    0.37
     rockers
    0.37
     ಸೇರಿದ
    0.37
    で開催
    0.36
    --(
    0.35
    comedy
    0.35
     yapılan
    0.35
     ससुराल
    0.35
    Act Density 0.007%

    No Known Activations