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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    provided
    -0.07
    .Session
    -0.07
     POW
    -0.07
     dbl
    -0.07
    <size
    -0.06
     rab
    -0.06
    rsp
    -0.06
     dunk
    -0.06
     Ras
    -0.06
     Chronicles
    -0.06
    POSITIVE LOGITS
    roys
    0.08
    perator
    0.06
    orses
    0.06
    ladesh
    0.06
    public
    0.06
     pháp
    0.06
    (()=>
    0.06
    ідно
    0.06
    ạnh
    0.06
    bserv
    0.06
    Act Density 0.000%

    No Known Activations