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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     surrender
    -0.88
     Surrender
    -0.75
     surrendered
    -0.66
     surrendering
    -0.63
     submission
    -0.57
    SceneManagement
    -0.55
     voluntarily
    -0.55
     willingly
    -0.55
     abandonment
    -0.52
     Submission
    -0.51
    POSITIVE LOGITS
     purpoſe
    0.60
    HideFlags
    0.60
    COUVER
    0.58
    XmlAccessorType
    0.56
     հղումներ
    0.54
    ownik
    0.54
     apreci
    0.52
    lawayo
    0.52
    Datuak
    0.51
    bitField
    0.51
    Act Density 0.012%

    No Known Activations