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

    Neuronpedia

    INDEX
    Explanations

    make sense or incorrect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    servicio
    0.47
    féle
    0.45
    قا
    0.44
    വൈ
    0.43
    лым
    0.43
     oiseaux
    0.42
    ково
    0.42
    𝚙
    0.42
     faits
    0.42
     électronique
    0.42
    POSITIVE LOGITS
     μπορεί
    0.47
     DIR
    0.46
     veya
    0.45
     debugging
    0.45
     или
    0.45
     dir
    0.44
     consonant
    0.44
     horsepower
    0.43
     din
    0.43
     closure
    0.42
    Act Density 0.009%

    No Known Activations