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

    Neuronpedia

    INDEX
    Explanations

    activation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     active
    -1.60
    activity
    -1.52
    active
    -1.47
     activity
    -1.40
     Active
    -1.35
    activ
    -1.31
    Active
    -1.30
     activation
    -1.25
     activate
    -1.22
    activation
    -1.20
    POSITIVE LOGITS
     متعلقه
    0.90
    ArgsConstructor
    0.78
    +#+#
    0.72
    AccessorTable
    0.68
     OFDb
    0.67
    mitian
    0.66
    PerformLayout
    0.63
     BorderRadius
    0.62
    IntoConstraints
    0.61
     predecess
    0.60
    Act Density 0.217%

    No Known Activations