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

    Neuronpedia

    INDEX
    Explanations

    Direct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aybe
    -0.07
    Thus
    -0.07
    Karen
    -0.06
     unst
    -0.06
    yan
    -0.06
    bpp
    -0.06
     بايد
    -0.06
    adj
    -0.06
     anlay
    -0.06
     wła
    -0.06
    POSITIVE LOGITS
     direct
    0.16
     Direct
    0.14
    Direct
    0.10
    direct
    0.09
    .Direct
    0.08
    instructions
    0.07
    .direct
    0.07
     DIRECT
    0.07
     dedicate
    0.07
    Controllers
    0.07
    Act Density 0.013%

    No Known Activations