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

    Neuronpedia

    INDEX
    Explanations

    generating content sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    儡
    1.44
    cale
    1.38
    忡
    1.36
    ا
    1.34
    ACTER
    1.26
    Ŭ
    1.24
    𝙚
    1.24
     "????.??.??"]
    1.23
    nj
    1.21
    里昂
    1.20
    POSITIVE LOGITS
    fl
    1.07
    г
    1.01
    callbacks
    1.00
    ChangedEventArgs
    0.98
    ant
    0.98
    ções
    0.97
    bel
    0.96
    grep
    0.96
    ions
    0.95
     موب
    0.95
    Act Density 0.000%

    No Known Activations