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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ắm
    -0.07
    175
    -0.07
    750
    -0.07
     confession
    -0.07
    ae
    -0.07
    938
    -0.06
     either
    -0.06
     benches
    -0.06
    文章
    -0.06
     animals
    -0.06
    POSITIVE LOGITS
     đèn
    0.06
     süt
    0.06
    (Photo
    0.06
    PKG
    0.06
    Routine
    0.06
    .processor
    0.06
     (){
    0.06
     Kültür
    0.06
     viêm
    0.06
    /on
    0.05
    Act Density 0.005%

    No Known Activations