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

    Neuronpedia

    INDEX
    Explanations

    research, evidence, logical, or loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intras
    0.41
    გილ
    0.40
     battalions
    0.40
    დილ
    0.39
     Fälle
    0.39
     pazienti
    0.39
     Stoll
    0.39
    .${
    0.38
    唑
    0.38
     Meade
    0.38
    POSITIVE LOGITS
    Blob
    0.43
    ốc
    0.41
    Starting
    0.39
    дан
    0.37
    质疑
    0.36
     ضرور
    0.36
    bucket
    0.36
    Mater
    0.36
    Not
    0.36
    Stat
    0.35
    Act Density 0.000%

    No Known Activations