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

    Neuronpedia

    INDEX
    Explanations

    limit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    剩
    -0.07
     дерева
    -0.07
    _DE
    -0.07
    Que
    -0.06
     birçok
    -0.06
     overpower
    -0.06
    embedding
    -0.06
    ang
    -0.06
    --------↵↵
    -0.06
    ひと
    -0.06
    POSITIVE LOGITS
    .blur
    0.07
     уп
    0.06
    .poly
    0.06
     ordinances
    0.06
    istencia
    0.06
    ầy
    0.06
    .array
    0.06
    Slash
    0.06
    .short
    0.06
    ()}}↵
    0.06
    Act Density 0.016%

    No Known Activations