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

    Neuronpedia

    INDEX
    Explanations

    ethical use and data management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    using
    0.54
    <b>
    0.46
    je
    0.46
    <h1>
    0.45
    Years
    0.45
    developed
    0.44
    Successfully
    0.44
    Amsterdam
    0.44
    Av
    0.44
    Member
    0.43
    POSITIVE LOGITS
    あくまで
    0.52
     paucity
    0.50
     onus
    0.48
     peculiarity
    0.46
     viti
    0.46
     vuelos
    0.46
     undue
    0.45
     aula
    0.45
     supposition
    0.44
     ponencia
    0.44
    Act Density 0.003%

    No Known Activations