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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uncomfortable
    -0.07
    wk
    -0.06
     سوال
    -0.06
     Rudy
    -0.06
     kısm
    -0.06
    dragon
    -0.06
     sortable
    -0.06
    �
    -0.06
     plumber
    -0.06
     diş
    -0.06
    POSITIVE LOGITS
     مدينة
    0.08
    Changed
    0.07
     Human
    0.07
    PATH
    0.07
    emperature
    0.06
     Goals
    0.06
     Goal
    0.06
    Energy
    0.06
    ()?.
    0.06
    Str
    0.06
    Act Density 0.011%

    No Known Activations