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

    Neuronpedia

    INDEX
    Explanations

    words related to events happening or being done, and proximity to numerical data.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -0.98
    ſelf
    -0.96
     purpoſe
    -0.94
     $_"
    -0.89
    ſelves
    -0.88
     Jefus
    -0.88
     <=",
    -0.87
    NUMX
    -0.85
     houſe
    -0.83
     itſelf
    -0.82
    POSITIVE LOGITS
     &
    0.58
     U
    0.56
     autorytatywna
    0.56
    terus
    0.56
    imakasih
    0.54
     -
    0.53
     K
    0.51
     S
    0.50
     tvar
    0.50
     
    0.50
    Act Density 2.367%

    No Known Activations