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

    Neuronpedia

    INDEX
    Explanations

    best locations, certain functions, RED vs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вом
    0.40
     fiel
    0.38
    เวล
    0.37
    мам
    0.35
     .(
    0.35
    Bienvenidos
    0.34
     הבי
    0.34
    ದ್
    0.34
     ****",
    0.34
    CheckedChanged
    0.34
    POSITIVE LOGITS
     zrobi
    0.37
     Sk
    0.36
     monitored
    0.35
    ību
    0.35
     Tug
    0.34
    馨
    0.34
    SCR
    0.34
     SCR
    0.34
     टो
    0.33
     Paola
    0.33
    Act Density 0.000%

    No Known Activations