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

    Neuronpedia

    INDEX
    Explanations

    writing components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    丢失
    0.50
    quiera
    0.49
    琊
    0.46
    ్యాన్ని
    0.44
    得到的
    0.44
    overs
    0.43
     segera
    0.42
     теря
    0.41
     Wasn
    0.41
    व्यापी
    0.40
    POSITIVE LOGITS
    Ionic
    0.53
    Votes
    0.51
    Architect
    0.50
    I
    0.50
     elution
    0.49
    Cell
    0.49
     ส
    0.49
    Arrows
    0.48
    Choisissez
    0.48
     arqué
    0.48
    Act Density 0.000%

    No Known Activations