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

    Neuronpedia

    INDEX
    Explanations

    sitting down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     befri
    0.51
    rale
    0.50
     muted
    0.46
     చ
    0.44
    されない
    0.43
    atir
    0.43
     outraged
    0.43
     TextAlign
    0.43
    ديد
    0.42
    దల
    0.42
    POSITIVE LOGITS
     ذمہ
    0.50
    Existing
    0.49
     wszystkie
    0.49
     bezpośred
    0.48
     anteriormente
    0.48
    NOTIFICATION
    0.47
    CEPTION
    0.46
     πρώτη
    0.46
     livello
    0.44
     penampilan
    0.44
    Act Density 0.000%

    No Known Activations