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

    Neuronpedia

    INDEX
    Explanations

    say "before"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🌳
    -0.08
    🖥
    -0.07
     brute
    -0.07
     ListViewItem
    -0.07
    庳
    -0.07
    warm
    -0.06
    כתב
    -0.06
     profes
    -0.06
     hoog
    -0.06
     Bloss
    -0.06
    POSITIVE LOGITS
    是非常
    0.08
    要进一步
    0.07
    .removeItem
    0.07
    landırıl
    0.07
     ).
    0.06
    нять
    0.06
    Comp
    0.06
    ◚
    0.06
     commenter
    0.06
    Nut
    0.06
    Act Density 0.003%

    No Known Activations