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

    Neuronpedia

    INDEX
    Explanations

    Calendar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     probe
    -0.07
     OSS
    -0.07
     treat
    -0.07
    StateToProps
    -0.07
     loss
    -0.07
     PF
    -0.07
    repos
    -0.07
     drugs
    -0.07
     samples
    -0.07
     repo
    -0.06
    POSITIVE LOGITS
     calendar
    0.14
     Calendar
    0.13
    Calendar
    0.12
    calendar
    0.11
     calendars
    0.10
    -calendar
    0.08
    лки
    0.07
    .calendar
    0.07
    (calendar
    0.07
     altar
    0.07
    Act Density 0.004%

    No Known Activations