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

    Neuronpedia

    INDEX
    Explanations

    magic bullet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    必定
    0.47
     diduga
    0.46
     generalmente
    0.46
    _{
    0.44
    必ず
    0.42
    似乎
    0.42
     geralmente
    0.41
     ocorre
    0.41
    往往
    0.41
     ہونے
    0.41
    POSITIVE LOGITS
     Asia
    0.56
     Huyền
    0.50
     Ridge
    0.48
    Asia
    0.46
     aven
    0.44
     knuckles
    0.44
    స్తూ
    0.44
     Blackberry
    0.43
    Phil
    0.43
     cuz
    0.43
    Act Density 0.003%

    No Known Activations