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

    Neuronpedia

    INDEX
    Explanations

    friendly competition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stethoscope
    0.69
     దర్శ
    0.66
     ورحمه
    0.64
     بوص
    0.63
     seedling
    0.61
    Trunc
    0.61
    Phenyl
    0.61
    اویز
    0.61
     kupu
    0.60
     seedlings
    0.60
    POSITIVE LOGITS
     fight
    4.17
     battle
    4.15
     battles
    4.10
     fights
    3.98
     fighting
    3.89
     fought
    3.75
     combat
    3.61
     Fight
    3.58
     battled
    3.57
    fight
    3.54
    Act Density 0.901%

    No Known Activations