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

    Neuronpedia

    INDEX
    Explanations

    say get

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    incl
    -0.07
    .setIcon
    -0.06
    attach
    -0.06
     init
    -0.06
     Covent
    -0.06
     AppDelegate
    -0.06
     Somebody
    -0.06
    .ny
    -0.06
    ogene
    -0.06
     Acc
    -0.06
    POSITIVE LOGITS
    蟮
    0.07
    秘
    0.07
    ꧁
    0.07
    affle
    0.07
    (Max
    0.07
    钻石
    0.07
    awah
    0.07
    ↵↵↵↵
    0.07
    andoned
    0.06
    ываем
    0.06
    Act Density 0.078%

    No Known Activations