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

    Neuronpedia

    INDEX
    Explanations

    death

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    czy
    -0.29
    èĽĩ
    -0.27
     kern
    -0.27
     weekends
    -0.27
    ç§ģ
    -0.26
    æĢİä¹Īçľĭ
    -0.26
    éļIJç§ģ
    -0.25
    çĻĸ
    -0.24
    ,private
    -0.24
    :error
    -0.23
    POSITIVE LOGITS
     Canton
    0.26
    logg
    0.25
     belonged
    0.25
     franca
    0.24
    berman
    0.24
     Affero
    0.23
    ackers
    0.23
    .yahoo
    0.23
    /release
    0.23
    resenter
    0.23
    Act Density 0.032%

    No Known Activations