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

    Neuronpedia

    INDEX
    Explanations

    people use the device

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     చేసింది
    0.45
    标
    0.44
    ybės
    0.41
    Putting
    0.39
     примеру
    0.39
    ">(
    0.38
    uš
    0.38
    ავს
    0.38
     വ്യക്തമാക്കി
    0.38
     первым
    0.37
    POSITIVE LOGITS
     din
    0.42
     Ông
    0.41
    SignedIn
    0.41
     architect
    0.41
     tiled
    0.40
     gle
    0.40
    ち
    0.39
    迌
    0.39
     희
    0.38
     tart
    0.38
    Act Density 0.000%

    No Known Activations