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

    Neuronpedia

    INDEX
    Explanations

    defining, influencing, questioning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     заве
    0.46
     a
    0.42
     ham
    0.41
     معلم
    0.41
     worried
    0.40
     pont
    0.40
    CLUSIVE
    0.39
    AD
    0.39
    सरकार
    0.39
     articulate
    0.38
    POSITIVE LOGITS
    Billboard
    0.47
    Lit
    0.46
    ñal
    0.46
    falling
    0.46
    ❉
    0.46
    ப்பும்
    0.45
    బ్బు
    0.45
    grabbing
    0.45
    ἓ
    0.44
    🖒
    0.44
    Act Density 0.002%

    No Known Activations