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

    Neuronpedia

    INDEX
    Explanations

    special list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     schrift
    0.57
    ábbi
    0.52
     Schrift
    0.48
     ആണ
    0.46
     allgemein
    0.45
     gesch
    0.45
     Sted
    0.45
     époque
    0.44
    ités
    0.44
     pů
    0.44
    POSITIVE LOGITS
    ל
    0.50
     ब्यूरो
    0.47
    mining
    0.46
    र्पण
    0.45
    मे
    0.44
    revolutionary
    0.44
     Pakistani
    0.43
     धोनी
    0.43
    दिया
    0.42
     तरह
    0.42
    Act Density 0.008%

    No Known Activations