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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🌼
    0.44
     honesty
    0.42
    Ꭳ
    0.41
     Burgh
    0.40
    లే
    0.39
    」，
    0.39
    기
    0.39
    బర్
    0.38
    :'',
    0.38
    cracker
    0.37
    POSITIVE LOGITS
     Schle
    0.40
     befindet
    0.39
     жив
    0.39
    set
    0.38
     matemat
    0.36
     অবি
    0.36
     MATH
    0.36
     первый
    0.36
    做的
    0.36
     bestimmt
    0.36
    Act Density 0.020%

    No Known Activations