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

    Neuronpedia

    INDEX
    Explanations

    purchase or device

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     up
    -0.77
    CloseOperation
    -0.60
     surla
    -0.59
    <bos>
    -0.58
    up
    -0.57
     out
    -0.56
     terenie
    -0.51
    apimachinery
    -0.47
     down
    -0.47
     away
    -0.47
    POSITIVE LOGITS
    AttributeSet
    0.60
     mapStateToProps
    0.54
    iální
    0.53
    ()%
    0.52
    !("{}",
    0.52
    gapi
    0.52
    rapie
    0.51
     createSlice
    0.50
    abestanden
    0.49
     astore
    0.49
    Act Density 0.040%

    No Known Activations