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

    Neuronpedia

    INDEX
    Explanations

    ROI, love, defensive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    С
    0.52
    РО
    0.50
    보
    0.47
    П
    0.47
    ukawa
    0.44
    ОВА
    0.43
    В
    0.43
    എ
    0.43
     BON
    0.43
    Е
    0.43
    POSITIVE LOGITS
     Junior
    0.45
     Hemat
    0.43
     Equals
    0.43
    gladbach
    0.40
     Defense
    0.40
     Defensive
    0.40
     defendant
    0.39
     deviceInfo
    0.39
     सही
    0.39
     Defendant
    0.39
    Act Density 0.003%

    No Known Activations