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

    Neuronpedia

    INDEX
    Explanations

    modeling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vamos
    -0.08
    fav
    -0.08
    אפ
    -0.08
    Concrete
    -0.08
     দেখি
    -0.08
     greet
    -0.08
     Credential
    -0.08
    യ്യ
    -0.07
     I'll
    -0.07
     mian
    -0.07
    POSITIVE LOGITS
     accuracy
    0.09
     approximation
    0.09
     promulg
    0.09
     inaccuracies
    0.08
     earbuds
    0.08
     accur
    0.08
     Woodland
    0.08
     accurate
    0.08
     precisão
    0.08
     equivalents
    0.08
    Act Density 0.005%

    No Known Activations