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
     News
    -0.07
     độc
    -0.07
     scenes
    -0.06
     operate
    -0.06
     cine
    -0.06
     hunts
    -0.06
    깡
    -0.06
    hält
    -0.06
    忒
    -0.06
    全力打造
    -0.06
    POSITIVE LOGITS
     encaps
    0.07
    ꡓ
    0.07
    很好地
    0.07
    য
    0.06
     stack
    0.06
    uggling
    0.06
    犯
    0.06
     outputStream
    0.06
    نغ
    0.06
    dap
    0.06
    Act Density 0.544%

    No Known Activations