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

    Neuronpedia

    INDEX
    Explanations

    Code/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     C
    -0.92
     W
    -0.91
     B
    -0.90
     Co
    -0.87
     Con
    -0.87
     De
    -0.86
     Ad
    -0.86
     Pe
    -0.85
     M
    -0.85
     Qu
    -0.85
    POSITIVE LOGITS
     myſelf
    1.52
     houſe
    1.37
     himſelf
    1.36
     raiſ
    1.36
     ſtate
    1.36
     itſelf
    1.35
     pleaſure
    1.34
     themſelves
    1.27
     étoient
    1.27
     poffible
    1.27
    Act Density 0.222%

    No Known Activations