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

    Neuronpedia

    INDEX
    Explanations

    places and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    뗀
    0.57
     docteur
    0.56
     epicenter
    0.55
     eigenvector
    0.54
     rø
    0.52
     filet
    0.52
     layoff
    0.52
    ड़ों
    0.51
     sporadic
    0.51
    рёх
    0.51
    POSITIVE LOGITS
    walk
    0.61
    atas
    0.61
    内的
    0.61
    goers
    0.60
    ifting
    0.57
    liness
    0.57
    𝘳
    0.57
     adalah
    0.56
    ның
    0.56
    settes
    0.55
    Act Density 0.152%

    No Known Activations