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

    Neuronpedia

    INDEX
    Explanations

    programming imports and data handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Metro
    0.49
    osito
    0.46
    繧
    0.45
    ্মা
    0.44
    MAN
    0.44
    ድግዳ
    0.44
    CHARGE
    0.44
    HUM
    0.43
    Mam
    0.42
     Dempsey
    0.42
    POSITIVE LOGITS
     collisions
    0.39
     könnt
    0.38
     Kolmogorov
    0.37
    ellik
    0.37
     lässt
    0.37
    是个
    0.37
     physicians
    0.37
    0.37
     tokamak
    0.37
    肴
    0.37
    Act Density 0.000%

    No Known Activations