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

    Neuronpedia

    INDEX
    Explanations

    title

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Crack
    -0.08
    egers
    -0.07
     scan
    -0.07
     Freeman
    -0.07
    Af
    -0.07
     κρα
    -0.07
     eo
    -0.06
     Check
    -0.06
     resource
    -0.06
     mMap
    -0.06
    POSITIVE LOGITS
     title
    0.11
    :title
    0.09
     titles
    0.09
    іл
    0.08
     Tit
    0.08
    .title
    0.08
    il
    0.08
     Title
    0.08
    틀
    0.08
    atetime
    0.08
    Act Density 0.036%

    No Known Activations