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

    Neuronpedia

    INDEX
    Explanations

    describes an entity or concept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    performed
    0.48
     деятельности
    0.46
     Teile
    0.44
     수행
    0.44
     portions
    0.43
     नौकरी
    0.42
    hatiti
    0.41
     performed
    0.40
     expenditures
    0.40
     روپے
    0.40
    POSITIVE LOGITS
     unleash
    0.36
    edia
    0.35
     bespoke
    0.35
     sbParams
    0.34
    Scientists
    0.33
     combinado
    0.33
    ಿಸುತ್ತ
    0.33
    urator
    0.33
    omatic
    0.33
    !
    0.33
    Act Density 0.000%

    No Known Activations