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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    main
    -0.07
    /INFO
    -0.07
    _bundle
    -0.06
     utilizando
    -0.06
     unsafe
    -0.06
    ञ
    -0.06
    .experimental
    -0.06
    识
    -0.06
     STL
    -0.06
    -len
    -0.06
    POSITIVE LOGITS
    抑郁症
    0.07
     desserts
    0.07
     Scale
    0.07
     passenger
    0.06
    viewer
    0.06
     Days
    0.06
    RH
    0.06
     TW
    0.06
    ㎟
    0.06
    רה
    0.06
    Act Density 0.041%

    No Known Activations