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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    규
    -0.08
    bidden
    -0.07
     SAC
    -0.07
    Parking
    -0.07
    ์อ
    -0.06
    .gs
    -0.06
    Marca
    -0.06
    -data
    -0.06
     forbidden
    -0.06
     Mouse
    -0.06
    POSITIVE LOGITS
     inflate
    0.07
     NUITKA
    0.07
    ктив
    0.06
    omore
    0.06
    taj
    0.06
     โปร
    0.06
    OOD
    0.06
    .ncbi
    0.06
     Var
    0.06
    ':'
    0.06
    Act Density 0.021%

    No Known Activations