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

    Neuronpedia

    INDEX
    Explanations

    Hadoop and aquariums

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.70
    с
    0.69
    ди
    0.68
    ığını
    0.67
    ز
    0.66
    ۰
    0.65
     тол
    0.64
    ，
    0.64
     дат
    0.61
     не
    0.61
    POSITIVE LOGITS
     was
    0.78
     Aquarium
    0.70
    lo
    0.69
     has
    0.68
     projects
    0.64
     is
    0.63
    NA
    0.63
     Projects
    0.63
    was
    0.62
    projects
    0.61
    Act Density 0.012%

    No Known Activations