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

    Neuronpedia

    INDEX
    Explanations

    new little

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Roskov
    -0.81
     feroit
    -0.79
     avoient
    -0.78
    routeProvider
    -0.72
    featureID
    -0.71
     InputDecoration
    -0.70
     étoient
    -0.69
     BorderSide
    -0.69
     auroit
    -0.69
     pouvoit
    -0.68
    POSITIVE LOGITS
     
    0.74
     set
    0.71
     bunch
    0.65
     section
    0.64
     group
    0.64
     batch
    0.64
     series
    0.63
     couple
    0.63
     pair
    0.62
     bit
    0.60
    Act Density 0.099%

    No Known Activations