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

    Neuronpedia

    INDEX
    Explanations

    ideas and proposals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    raine
    0.74
    ння
    0.69
    ong
    0.66
    п
    0.63
    ละ
    0.60
    ly
    0.59
     respiratory
    0.59
    robe
    0.59
    tered
    0.59
    ές
    0.58
    POSITIVE LOGITS
     idee
    1.05
     ideas
    1.00
     proposta
    1.00
     идеи
    0.94
     proposals
    0.92
     öner
    0.92
     idées
    0.91
     idea
    0.88
    提案
    0.88
    ideas
    0.86
    Act Density 0.487%

    No Known Activations