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

    Neuronpedia

    INDEX
    Explanations

    C++ or related code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ḵ
    0.42
    ine
    0.39
    neq
    0.39
     Korn
    0.39
    Җ
    0.38
    icol
    0.37
     ioe
    0.37
    ^{*}}{\
    0.37
    ^{*}$,
    0.36
     doj
    0.36
    POSITIVE LOGITS
     physique
    0.57
     PubMed
    0.57
    曩
    0.54
     accountable
    0.52
     Fantastic
    0.52
     hyperlink
    0.51
     obtainable
    0.51
     Whilst
    0.47
     utilised
    0.46
    Fantastic
    0.46
    Act Density 0.001%

    No Known Activations