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

    Neuronpedia

    INDEX
    Explanations

    department

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     close
    -1.23
     Close
    -1.17
     department
    -1.16
    Close
    -1.05
    close
    -1.04
     CLOSE
    -1.02
     clos
    -1.01
    department
    -0.94
     CLOS
    -0.94
    tics
    -0.89
    POSITIVE LOGITS
     of
    0.69
     for
    0.56
    ProgressHUD
    0.46
    वार
    0.43
    llä
    0.42
    这款
    0.42
     and
    0.41
     por
    0.41
     messen
    0.41
    PLAC
    0.41
    Act Density 0.157%

    No Known Activations