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

    Neuronpedia

    INDEX
    Explanations

    data filtering/smoothing algorithms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    幽
    -0.09
    (ob
    -0.08
     Nig
    -0.08
     safe
    -0.07
    (Server
    -0.07
    限
    -0.07
     safer
    -0.07
    (Name
    -0.07
     пу
    -0.07
    (variable
    -0.07
    POSITIVE LOGITS
     Aerospace
    0.08
     storefront
    0.08
    Maint
    0.07
     thư
    0.07
     aerospace
    0.07
     איינ
    0.07
    /[
    0.07
     Flug
    0.07
     వెల
    0.07
     вт
    0.07
    Act Density 0.000%

    No Known Activations