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

    Neuronpedia

    INDEX
    Explanations

    than explore, that year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ３
    0.59
    ８
    0.54
    8
    0.52
    ２
    0.52
    ４
    0.52
     tijd
    0.50
    ７
    0.50
    ٥
    0.49
    AN
    0.49
    チ
    0.49
    POSITIVE LOGITS
    uo
    0.58
    tu
    0.52
     CtApp
    0.50
    s
    0.49
     )
    0.49
    se
    0.46
     }
    0.46
     coexist
    0.46
    tbLabel
    0.45
     appease
    0.43
    Act Density 0.000%

    No Known Activations