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

    Neuronpedia

    INDEX
    Explanations

    say damages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phổ
    -0.09
     coherence
    -0.08
    枣
    -0.08
     passphrase
    -0.07
     lobster
    -0.07
     véritable
    -0.07
     Black
    -0.07
    tri
    -0.07
     dép
    -0.07
     propre
    -0.07
    POSITIVE LOGITS
    )");
↵
    0.07
    }");↵
    0.07
    Rare
    0.07
    ONGL
    0.07
    forg
    0.07
    _;
↵
    0.06
     Meghan
    0.06
    >')↵
    0.06
    껸
    0.06
    当下
    0.06
    Act Density 0.001%

    No Known Activations