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

    Neuronpedia

    INDEX
    Explanations

    feature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     feature
    -1.20
    ters
    -0.96
    feature
    -0.91
     offering
    -0.90
     Feature
    -0.90
     FEATURE
    -0.85
     Offering
    -0.82
     offerings
    -0.82
    Feature
    -0.81
    Offering
    -0.79
    POSITIVE LOGITS
    UIControlState
    0.73
    XmlAccessType
    0.60
    struts
    0.60
    TagMode
    0.58
     &___
    0.57
    SourceChecksum
    0.56
     consultato
    0.54
    dafx
    0.53
    occuper
    0.52
     Infórmanos
    0.51
    Act Density 0.273%

    No Known Activations