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

    Neuronpedia

    INDEX
    Explanations

    Showing Up for Racial Justice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     revitalize
    0.53
     criticize
    0.48
     siquiera
    0.46
    ר
    0.45
     quieren
    0.44
     invigorating
    0.44
    ﺒ
    0.44
     recognize
    0.44
     invigor
    0.43
     quieras
    0.43
    POSITIVE LOGITS
    ton
    0.54
    -
    0.47
    ты
    0.45
    ly
    0.44
    ла
    0.43
    redients
    0.42
     Implementing
    0.41
    rades
    0.40
    ↵↵
    0.38
    ta
    0.38
    Act Density 0.042%

    No Known Activations