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

    Neuronpedia

    INDEX
    Explanations

    elected

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deposition
    -0.08
     averaging
    -0.07
    Dia
    -0.07
    ToUpdate
    -0.07
     starting
    -0.07
     전
    -0.06
     Drops
    -0.06
     MCP
    -0.06
     dinner
    -0.06
    Fan
    -0.06
    POSITIVE LOGITS
     †
    0.07
    нівер
    0.06
     τις
    0.06
    NSSet
    0.06
    _emlrt
    0.06
    perial
    0.06
    (ir
    0.06
    quota
    0.06
    inish
    0.06
    than
    0.06
    Act Density 0.067%

    No Known Activations