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

    Neuronpedia

    INDEX
    Explanations

    tragic popular defines Love what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    T
    0.49
     inversión
    0.47
     ওয়ে
    0.46
     Lover
    0.45
    Php
    0.45
     costos
    0.44
     industria
    0.44
    g
    0.44
    成本
    0.43
     rendement
    0.43
    POSITIVE LOGITS
    erves
    0.44
    plicial
    0.42
    ხვა
    0.42
    스크
    0.41
    erved
    0.41
    ════
    0.41
    츠
    0.41
     sizable
    0.40
    :”
    0.40
    sembled
    0.39
    Act Density 0.003%

    No Known Activations