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

    Neuronpedia

    INDEX
    Explanations

    LaTeX document structure

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Extended
    0.61
    Abstract
    0.55
    bare
    0.54
    ginger
    0.54
     Fuer
    0.52
    Highlights
    0.52
    Hö
    0.52
     Correspond
    0.52
     Correspondence
    0.52
    Functional
    0.52
    POSITIVE LOGITS
     içi
    0.57
     заг
    0.56
     largeur
    0.56
     bfs
    0.54
     escultura
    0.54
     emitter
    0.54
     imprensa
    0.53
    كلة
    0.53
    嚀
    0.53
     escult
    0.52
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.