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

    Neuronpedia

    INDEX
    Explanations

    not speaking full sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     E
    0.50
     Ε
    0.46
     Ald
    0.45
     H
    0.43
     colonies
    0.43
     Image
    0.41
     Admiral
    0.41
     outages
    0.40
    是因為
    0.40
     Armor
    0.40
    POSITIVE LOGITS
    physiology
    0.53
    들을
    0.51
    before
    0.51
     finanzi
    0.48
     stipend
    0.46
    passing
    0.46
    <0x00>
    0.46
     before
    0.45
    him
    0.45
     בין
    0.45
    Act Density 0.002%

    No Known Activations