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

    Neuronpedia

    INDEX
    Explanations

    functional language concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kiedy
    0.39
     representado
    0.38
    色の
    0.37
     commencent
    0.36
     खासा
    0.36
    πό
    0.36
    দির
    0.36
    URO
    0.35
    ণ্ডের
    0.35
     indef
    0.35
    POSITIVE LOGITS
     sendiri
    0.46
     Own
    0.44
     মতামত
    0.40
     Custom
    0.40
    own
    0.40
     jaw
    0.39
    hetamine
    0.39
     włas
    0.38
     অথবা
    0.38
    了吗
    0.38
    Act Density 0.000%

    No Known Activations