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

    Neuronpedia

    INDEX
    Explanations

    Technical writing/instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lev
    -0.07
     enthusi
    -0.06
    byterian
    -0.06
    utra
    -0.06
     cemetery
    -0.06
     lesb
    -0.06
     kdo
    -0.06
    THR
    -0.06
     brittle
    -0.06
    otec
    -0.06
    POSITIVE LOGITS
     filling
    0.07
    不到
    0.07
     Nev
    0.07
     Basics
    0.07
    _base
    0.07
     funds
    0.06
     Elements
    0.06
     -=
    0.06
     accommodation
    0.06
    .byte
    0.06
    Act Density 0.000%

    No Known Activations