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

    Neuronpedia

    INDEX
    Explanations

    being or something followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Consulate
    0.44
     Creators
    0.42
     createFile
    0.41
    ActionsCallback
    0.40
     Фу
    0.40
     Italy
    0.39
    órc
    0.38
     Brittany
    0.38
     معانا
    0.38
     Britain
    0.37
    POSITIVE LOGITS
     scrutin
    0.41
     assent
    0.39
     supervision
    0.38
    switching
    0.38
     schl
    0.38
     wondered
    0.38
     rede
    0.37
     diarios
    0.37
    Step
    0.37
    Slf
    0.37
    Act Density 0.001%

    No Known Activations