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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    appar
    -0.08
     marinade
    -0.08
    nes
    -0.08
     rejection
    -0.07
     Loom
    -0.07
     архив
    -0.07
     imperfections
    -0.07
     axes
    -0.07
     ਐ
    -0.07
     बीमारी
    -0.07
    POSITIVE LOGITS
     TK
    0.08
     administrativo
    0.08
     MG
    0.08
     bäst
    0.08
    凯
    0.07
    百分
    0.07
    piej
    0.07
     esquer
    0.07
     subcon
    0.07
     প্রদান
    0.07
    Act Density 0.024%

    No Known Activations