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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    日本
    -0.07
     enhanced
    -0.07
    روج
    -0.07
    оды
    -0.07
    times
    -0.07
     Ông
    -0.07
     bonds
    -0.06
    enable
    -0.06
     самым
    -0.06
     durante
    -0.06
    POSITIVE LOGITS
     Disqus
    0.08
     Swing
    0.06
     ballistic
    0.06
    KM
    0.06
     invit
    0.06
     GPL
    0.06
     narc
    0.05
     произ
    0.05
    dez
    0.05
     교
    0.05
    Act Density 0.022%

    No Known Activations