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

    Neuronpedia

    INDEX
    Explanations

    breakdown and categorization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     också
    0.36
     bajos
    0.36
     також
    0.36
     бана
    0.36
    אם
    0.34
     คะแนน
    0.34
     أيضا
    0.34
     সামান্য
    0.33
    ᅩ
    0.33
     benefícios
    0.32
    POSITIVE LOGITS
    guide
    0.42
     discusses
    0.39
     विवे
    0.39
     explores
    0.39
     विश्लेषण
    0.38
     จัด
    0.38
    ​,
    0.38
    >,
    0.38
    Guide
    0.37
     explore
    0.37
    Act Density 0.356%

    No Known Activations