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

    Neuronpedia

    INDEX
    Explanations

    exception handling using e:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meningkat
    1.44
     iyo
    1.33
     egos
    1.31
    ್ಟ
    1.27
    Dalam
    1.24
    dalam
    1.24
     masyarakat
    1.23
     matahari
    1.23
     Namun
    1.22
     khususnya
    1.22
    POSITIVE LOGITS
    한
    1.14
    έ
    1.06
    w
    1.02
    环境保护
    1.00
    문
    0.99
    ord
    0.99
    ö
    0.98
     folgenden
    0.98
     allgemeinen
    0.97
    éch
    0.95
    Act Density 0.098%

    No Known Activations