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

    Neuronpedia

    INDEX
    Explanations

    HTML tags, code injection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ubei
    0.42
    being
    0.41
    صول
    0.41
    eka
    0.40
    צב
    0.40
    altung
    0.40
    idia
    0.40
    uns
    0.39
    iding
    0.39
    unu
    0.39
    POSITIVE LOGITS
     arrend
    0.39
     subsonic
    0.39
     повече
    0.38
     Aéroport
    0.38
     buttery
    0.38
     pog
    0.37
     noticia
    0.37
     communic
    0.37
     isLoggedIn
    0.37
     hasher
    0.37
    Act Density 0.016%

    No Known Activations