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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     humour
    -0.08
     frequency
    -0.07
     mixture
    -0.07
     tumor
    -0.07
     durations
    -0.07
    Fat
    -0.07
    Samples
    -0.07
     tumors
    -0.07
     sample
    -0.07
     rhythm
    -0.06
    POSITIVE LOGITS
    0.07
    0.07
    SCRI
    0.07
     pursuant
    0.07
     libertin
    0.06
    0.06
    JKLM
    0.06
    enschaft
    0.06
    .LabelControl
    0.06
     SwiftUI
    0.06
    Act Density 0.005%

    No Known Activations