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

    Neuronpedia

    INDEX
    Explanations

    k

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ñana
    -0.07
     obvious
    -0.07
    obbies
    -0.07
    IES
    -0.06
    fullName
    -0.06
     mandates
    -0.06
    ies
    -0.06
     bene
    -0.06
    Sep
    -0.06
    fixtures
    -0.06
    POSITIVE LOGITS
     Ren
    0.07
     LC
    0.07
    ='${
    0.06
     Elem
    0.06
     DSL
    0.06
     Harmon
    0.06
    down
    0.06
     EVER
    0.06
     Гол
    0.06
     TOM
    0.06
    Act Density 0.001%

    No Known Activations