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

    Neuronpedia

    INDEX
    Explanations

    this [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ης
    1.52
    ан
    1.45
    م
    1.42
    ش
    1.42
    说
    1.36
     aDict
    1.30
     commenc
    1.29
    EZ
    1.29
    ER
    1.26
     quotients
    1.25
    POSITIVE LOGITS
     وهذه
    2.77
     وهذا
    2.23
    pt
    1.76
    at
    1.40
    durch
    1.36
    ere
    1.28
    nione
    1.27
    ત્મ
    1.26
    istä
    1.24
    cc
    1.22
    Act Density 0.940%

    No Known Activations