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

    Neuronpedia

    INDEX
    Explanations

    TH

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arena
    -0.07
    ersed
    -0.07
     ad
    -0.07
     detects
    -0.07
    basis
    -0.07
     getC
    -0.07
     situ
    -0.06
    AKER
    -0.06
    Cs
    -0.06
     intern
    -0.06
    POSITIVE LOGITS
     StringType
    0.07
     Českosloven
    0.07
     kaldı
    0.06
     İngiltere
    0.06
    'user
    0.06
     адміністратив
    0.06
     htmlFor
    0.06
     IList
    0.06
     boasted
    0.06
     매
    0.06
    Act Density 0.081%

    No Known Activations