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

    Neuronpedia

    INDEX
    Explanations

    new healthy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     this
    -1.18
     Uso
    -1.13
    шении
    -1.13
    ⇐
    -1.05
    isso
    -1.02
    ⇨
    -1.02
     EDIT
    -1.01
     these
    -1.01
     CGRectMake
    -1.00
    ,
    -1.00
    POSITIVE LOGITS
     photos
    1.29
     oči
    1.24
     reflexiones
    1.18
     nový
    1.13
    给大家
    1.11
     official
    1.10
    怎么回事
    1.09
     enfermera
    1.07
     및
    1.06
    Переваги
    1.06
    Act Density 0.000%

    No Known Activations