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

    Neuronpedia

    INDEX
    Explanations

    .env files and environment variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Resolver
    0.51
    Resolver
    0.46
    utom
    0.44
     Updater
    0.44
     geändert
    0.44
     PlayerSelector
    0.42
     DELETE
    0.41
     GitLab
    0.41
    朖
    0.40
    변경
    0.39
    POSITIVE LOGITS
     vars
    0.45
     variables
    0.44
     VARIABLES
    0.42
     chocolates
    0.39
    principles
    0.38
    variables
    0.38
    vars
    0.38
     Maris
    0.38
     कम्
    0.38
     carvings
    0.37
    Act Density 0.000%

    No Known Activations