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

    Neuronpedia

    INDEX
    Explanations

    significance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :{
↵
    -0.07
     bý
    -0.06
     karşılaş
    -0.06
     привести
    -0.06
    .destination
    -0.06
     Winners
    -0.06
     Lucky
    -0.06
     کش
    -0.06
     RedirectTo
    -0.06
     */;↵
    -0.06
    POSITIVE LOGITS
    ‑
    0.07
     signify
    0.07
     meaningful
    0.07
     esteemed
    0.07
    .chapter
    0.06
     seminars
    0.06
     suede
    0.06
     interpolation
    0.06
     IMPLEMENT
    0.06
    eload
    0.06
    Act Density 0.027%

    No Known Activations