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

    Neuronpedia

    INDEX
    Explanations

    probability adverbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bv
    -0.06
     Üst
    -0.06
    дав
    -0.06
     mel
    -0.06
    σκευή
    -0.06
    _sorted
    -0.06
    ивать
    -0.06
     opt
    -0.06
    lessons
    -0.06
     itens
    -0.06
    POSITIVE LOGITS
    sometimes
    0.07
    诊
    0.07
    $(
    0.06
    尿
    0.06
    inston
    0.06
    Currently
    0.06
    edom
    0.06
    hammad
    0.06
     transplant
    0.06
    REDIT
    0.06
    Act Density 0.052%

    No Known Activations