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

    Neuronpedia

    INDEX
    Explanations

    foreign words and abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    раль
    0.45
     Mikolai
    0.40
    bigskip
    0.40
    ニチイ
    0.38
     cyclase
    0.38
     jamb
    0.38
     argparse
    0.38
    pF
    0.37
    imiter
    0.37
    ادار
    0.37
    POSITIVE LOGITS
    红色
    0.39
     Phenomen
    0.39
     Symbolic
    0.38
    新宿
    0.38
     inexplicable
    0.38
    紅色
    0.37
     흰
    0.37
     अमन
    0.35
    וריה
    0.35
     unexplained
    0.35
    Act Density 0.004%

    No Known Activations