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

    Neuronpedia

    INDEX
    Explanations

    writings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.47
     par
    -0.44
     skut
    -0.43
    anasia
    -0.42
     Effect
    -0.39
     Activity
    -0.39
    PostMapping
    -0.39
    IBOutlet
    -0.39
    Control
    -0.39
    par
    -0.39
    POSITIVE LOGITS
    #+#
    1.06
     propOrder
    0.73
    RegressionTest
    0.70
    +#+
    0.67
     tartalomajánló
    0.66
     language
    0.65
     Langu
    0.64
    zzleHttp
    0.63
     Архів
    0.61
    énario
    0.60
    Act Density 0.001%

    No Known Activations