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

    Neuronpedia

    INDEX
    Explanations

    reopened after, real value, end transition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ・
    0.45
    ik
    0.44
    搬
    0.44
    供
    0.43
    QC
    0.43
    AB
    0.42
    Instagram
    0.41
    SSL
    0.41
    Collapse
    0.41
    Assume
    0.41
    POSITIVE LOGITS
    ეგის
    0.50
     اصحاب
    0.47
     วิ
    0.46
    堑
    0.45
     asoci
    0.45
     będą
    0.44
    kiego
    0.44
     πίνα
    0.44
     bani
    0.44
     admis
    0.44
    Act Density 0.001%

    No Known Activations