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

    Neuronpedia

    INDEX
    Explanations

    phrases after specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    萨
    0.52
    ARR
    0.52
    สาร
    0.52
    艐
    0.49
     ﺍ
    0.49
     Larn
    0.47
    ADO
    0.47
     Sabha
    0.46
     Arik
    0.46
     actividades
    0.45
    POSITIVE LOGITS
    there
    0.48
    am
    0.45
    spaces
    0.45
    hão
    0.45
     جبکہ
    0.44
     ആരോഗ്യ
    0.44
    vill
    0.43
    arg
    0.42
    ai
    0.42
    false
    0.42
    Act Density 0.000%

    No Known Activations